2024

KISS-Matcher: Fast and Robust Point Cloud Registration Revisited

Hyungtae Lim, Daebeom Kim, Gunhee Shin, Jingnan Shi, Ignacio Vizzo, Hyun Myung, Jaesik Park, and Luca Carlone. 2409.15615 (arXiv), 2024
StarFork

Paper Code

@article{Lim_KISSMatcher_arXiv_2024,
Title={KISS-Matcher: Fast and Robust Point Cloud Registration Revisited},
Author={Hyungtae Lim and Daebeom Kim and Gunhee Shin and Jingnan Shi and Ignacio Vizzo and Hyun Myung and Jaesik Park and Luca Carlone},
Journal={2409.15615 (arXiv)},
Year={2024}
}

Budget-Aware Sequential Brick Assembly with Efficient Constraint Satisfaction

Seokjun Ahn*, Jungtaek Kim*, Minsu Cho, and Jaesik Park. Transactions on Machine Learning Research (TMLR), 2024
(*Joint first authors)

@article{Ahn_BudgetAware_TMLR_2024,
Title={Budget-Aware Sequential Brick Assembly with Efficient Constraint Satisfaction},
Author={Seokjun Ahn and Jungtaek Kim and Minsu Cho and Jaesik Park},
Journal={Transactions on Machine Learning Research (TMLR)},
Year={2024}
}

InstantDrag: Improving Interactivity in Drag-based Image Editing

Joonghyuk Shin, Daehyeon Choi, and Jaesik Park. ACM Special Interest Group on Graphics and Interactive Techniques (SIGGRAPH Asia), 2024
StarFork

Project Page Code

@inproceedings{Shin_InstantDrag_SIGGRAPH_Asia_2024,
Title={InstantDrag: Improving Interactivity in Drag-based Image Editing},
Author={Joonghyuk Shin and Daehyeon Choi and Jaesik Park},
Booktitle={Proceedings of the ACM Special Interest Group on Graphics and Interactive Techniques (SIGGRAPH Asia)},
Year={2024}
}

Distilling Diffusion Models into Conditional GANs

Minguk Kang, Richard Zhang, Connelly Barnes, Sylvain Paris, Suha Kwak, Jaesik Park, Eli Shechtman, Jun-Yan Zhu, and Taesung Park. European Conf. on Computer Vision (ECCV), 2024

Project Page Paper Code

@inproceedings{Kang_Distilling_ECCV_2024,
Title={Distilling Diffusion Models into Conditional GANs},
Author={Minguk Kang and Richard Zhang and Connelly Barnes and Sylvain Paris and Suha Kwak and Jaesik Park and Eli Shechtman and Jun-Yan Zhu and Taesung Park},
Booktitle={Proceedings of the European Conf. on Computer Vision (ECCV)},
Year={2024}
}

Deep Cost Ray Fusion for Sparse Depth Video Completion

Jungeon Kim, Soongjin Kim, Jaesik Park, and Seungyong Lee. European Conf. on Computer Vision (ECCV), 2024

@inproceedings{Kim_Deep_ECCV_2024,
Title={Deep Cost Ray Fusion for Sparse Depth Video Completion},
Author={Jungeon Kim and Soongjin Kim and Jaesik Park and Seungyong Lee},
Booktitle={Proceedings of the European Conf. on Computer Vision (ECCV)},
Year={2024}
}

3D Geometric Shape Assembly via Efficient Point Cloud Matching

Nahyuk Lee, Juhong Min, Junha Lee, Seungwook Kim, Kanghee Lee, Jaesik Park, and Minsu Cho. Int. Conf. on Machine Learning (ICML), 2024

Project Page Paper Code

@inproceedings{Lee_3D_ICML_2024,
Title={3D Geometric Shape Assembly via Efficient Point Cloud Matching},
Author={Nahyuk Lee and Juhong Min and Junha Lee and Seungwook Kim and Kanghee Lee and Jaesik Park and Minsu Cho},
Booktitle={Proceedings of the Int. Conf. on Machine Learning (ICML)},
Year={2024}
}

3Doodle: Compact Abstraction of Objects with 3D Strokes

Changwoon Choi, Jaeah Lee, Jaesik Park, and Young Min Kim. ACM Special Interest Group on Graphics and Interactive Techniques (SIGGRAPH), 2024
(Accepted as a journal track paper)

Project Page Paper Code

@inproceedings{Choi_3Doodle_SIGGRAPH_2024,
Title={3Doodle: Compact Abstraction of Objects with 3D Strokes},
Author={Changwoon Choi and Jaeah Lee and Jaesik Park and Young Min Kim},
Booktitle={Proceedings of the ACM Special Interest Group on Graphics and Interactive Techniques (SIGGRAPH)},
Year={2024}
}

Extending CLIP's Image-Text Alignment to Referring Image Segmentation

Seoyeon Kim, Minguk Kang, Dongwon Kim, Jaesik Park, and Suha Kwak. Annual Conf. of the North American Chapter of the Assoc. for Computational Linguistics (NAACL), 2024

Paper

@inproceedings{Kim_Extending_NAACL_2024,
Title={Extending CLIP's Image-Text Alignment to Referring Image Segmentation},
Author={Seoyeon Kim and Minguk Kang and Dongwon Kim and Jaesik Park and Suha Kwak},
Booktitle={Proceedings of the Annual Conf. of the North American Chapter of the Assoc. for Computational Linguistics (NAACL)},
Year={2024}
}

Pick-or-Mix: Dynamic Channel Sampling for ConvNets

Ashish Kumar, Daneul Kim, Jaesik Park, and Laxmidhar Behera. Int. Conf. on Computer Vision and Pattern Recognition (CVPR), 2024

Paper Code

@inproceedings{Kumar_PickorMix_CVPR_2024,
Title={Pick-or-Mix: Dynamic Channel Sampling for ConvNets},
Author={Ashish Kumar and Daneul Kim and Jaesik Park and Laxmidhar Behera},
Booktitle={Proceedings of the Int. Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2024}
}

Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform

Chunghyun Park, Seungwook Kim, Jaesik Park, and Minsu Cho. Int. Conf. on Computer Vision and Pattern Recognition (CVPR), 2024

Paper

@inproceedings{Park_Learning_CVPR_2024,
Title={Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform},
Author={Chunghyun Park and Seungwook Kim and Jaesik Park and Minsu Cho},
Booktitle={Proceedings of the Int. Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2024}
}

High-Speed Stereo Visual SLAM for Low-Powered Computing Devices

Ashish Kumar, Jaesik Park, and Laxmidhar Behera. IEEE Robotics and Automation Letters (RAL), vol. 9, issue 1, 2024
(invited to the ICRA2024 oral presentation)

Paper Code

@article{Kumar_HighSpeed_RAL_2024,
Title={High-Speed Stereo Visual SLAM for Low-Powered Computing Devices},
Author={Ashish Kumar and Jaesik Park and Laxmidhar Behera},
Journal={IEEE Robotics and Automation Letters (RAL), vol. 9, issue 1},
Year={2024}
}


2023

Binary Radiance Fields

Seungjoo Shin and Jaesik Park. Conf. on Neural Information Processing Systems (NeurIPS), 2023
(Received 30th HumanTech Paper Award (Silver Prize), Samsung Electronics Corp.)

Project Page Paper Code

@inproceedings{Shin_Binary_NeurIPS_2023,
Title={Binary Radiance Fields},
Author={Seungjoo Shin and Jaesik Park},
Booktitle={Proceedings of the Conf. on Neural Information Processing Systems (NeurIPS)},
Year={2023}
}

StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis

MinGuk Kang, Joonghyuk Shin, and Jaesik Park. Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
StarFork

Paper Code

@article{Kang_StudioGAN_TPAMI_2023,
Title={StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis},
Author={MinGuk Kang and Joonghyuk Shin and Jaesik Park},
Journal={Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
Year={2023}
}

Spacetime Surface Regularization for Neural Dynamic Scene Reconstruction

Jaesung Choe, Christopher Choy, Jaesik Park, In So Kweon, and Animashree Anandkumar. Int. Conf. on Computer Vision (ICCV), 2023

Paper

@inproceedings{Choe_Spacetime_ICCV_2023,
Title={Spacetime Surface Regularization for Neural Dynamic Scene Reconstruction},
Author={Jaesung Choe and Christopher Choy and Jaesik Park and In So Kweon and Animashree Anandkumar},
Booktitle={Proceedings of the Int. Conf. on Computer Vision (ICCV)},
Year={2023}
}

Fill-Up: Balancing Long-Tailed Data with Generative Models

Joonghyuk Shin, Minguk Kang, and Jaesik Park. 2306.07200 (arXiv), 2023

Project Page Paper

@article{Shin_FillUp_arXiv_2023,
Title={Fill-Up: Balancing Long-Tailed Data with Generative Models},
Author={Joonghyuk Shin and Minguk Kang and Jaesik Park},
Journal={2306.07200 (arXiv)},
Year={2023}
}

RISCLIP: Referring Image Segmentation Framework using CLIP

Seoyeon Kim, Minguk Kang, and Jaesik Park. 2306.08498 (arXiv), 2023

Paper

@article{Kim_RISCLIP_arXiv_2023,
Title={RISCLIP: Referring Image Segmentation Framework using CLIP},
Author={Seoyeon Kim and Minguk Kang and Jaesik Park},
Journal={2306.08498 (arXiv)},
Year={2023}
}

Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learning

Seungwook Kim, Chunghyun Park, Yoonwoo Jeong, Jaesik Park, and Minsu Cho. Int. Conf. on Machine Learning (ICML), 2023

Paper

@inproceedings{Kim_Stable_ICML_2023,
Title={Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learning},
Author={Seungwook Kim and Chunghyun Park and Yoonwoo Jeong and Jaesik Park and Minsu Cho},
Booktitle={Proceedings of the Int. Conf. on Machine Learning (ICML)},
Year={2023}
}

Scaling up GANs for Text-to-Image Synthesis

Minguk Kang, Jun-Yan Zhu, Richard Zhang, Jaesik Park, Eli Shechtman, Sylvain Paris, and Taesung Park. Int. Conf. on Computer Vision and Pattern Recognition (CVPR), 2023
(Accepted as a highlight paper (review score 5,5,5) - top 2.5% among 9,155 submissions)

Project Page Paper

@inproceedings{Kang_Scaling_CVPR_2023,
Title={Scaling up GANs for Text-to-Image Synthesis},
Author={Minguk Kang and Jun-Yan Zhu and Richard Zhang and Jaesik Park and Eli Shechtman and Sylvain Paris and Taesung Park},
Booktitle={Proceedings of the Int. Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2023}
}

Instant Domain Augmentation for LiDAR Semantic Segmentation

Kwonyoung Ryu, Soonmin Hwang, and Jaesik Park. Int. Conf. on Computer Vision and Pattern Recognition (CVPR), 2023

Paper

@inproceedings{Ryu_Instant_CVPR_2023,
Title={Instant Domain Augmentation for LiDAR Semantic Segmentation},
Author={Kwonyoung Ryu and Soonmin Hwang and Jaesik Park},
Booktitle={Proceedings of the Int. Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2023}
}

Learning to Register Unbalanced Point Pairs

Kanghee Lee, Junha Lee, and Jaesik Park. 3D Vision and Robotics CVPR workshop, 2023

Paper

@inproceedings{Lee_Learning_3D_Vision_and_Robotics_CVPR_workshop Title={Learning to Register Unbalanced Point Pairs},
Author={Kanghee Lee and Junha Lee and Jaesik Park},
Booktitle={Proceedings of the 3D Vision and Robotics CVPR workshop},
Year={2023}
}

Instance-Aware Image Completion

Jinoh Cho, Minguk Kang, Vibhav Vineet, and Jaesik Park. AI for Content Creation (AI4CC) CVPR workshop, 2023

Paper

@inproceedings{Cho_InstanceAware_AI4CC_2023,
Title={Instance-Aware Image Completion},
Author={Jinoh Cho and Minguk Kang and Vibhav Vineet and Jaesik Park},
Booktitle={Proceedings of the AI for Content Creation (AI4CC) CVPR workshop},
Year={2023}
}

Scene-level Point Cloud Colorization with Semantic-and-Geometric-aware Networks

Rongrong Gao, Tian-Zhu Xiang, Chenyang Lei, Jaesik Park, and Qifeng Chen. IEEE Int. Conf. on Robotics and Automation (ICRA), 2023

@inproceedings{Gao_Scenelevel_ICRA_2023,
Title={Scene-level Point Cloud Colorization with Semantic-and-Geometric-aware Networks},
Author={Rongrong Gao and Tian-Zhu Xiang and Chenyang Lei and Jaesik Park and Qifeng Chen},
Booktitle={Proceedings of the IEEE Int. Conf. on Robotics and Automation (ICRA)},
Year={2023}
}

Deep 3D Reconstruction of Synchrotron X-ray Computed Tomography for Intact Lungs

Seungjoo Shin*, Min Woo Kim*, Kyong Hwan Jin, Kwang Moo Yi, Yoshiki Kohmura, Tetsuya Ishikawa, Jung Ho Je, and Jaesik Park. published by Nature Research (Scientific Reports), 2023
(*Equal contribution)

Paper

@article{Shin_Deep_Scientific_Reports_2023,
Title={Deep 3D Reconstruction of Synchrotron X-ray Computed Tomography for Intact Lungs},
Author={Seungjoo Shin and Min Woo Kim and Kyong Hwan Jin and Kwang Moo Yi and Yoshiki Kohmura and Tetsuya Ishikawa and Jung Ho Je and Jaesik Park},
Journal={published by Nature Research (Scientific Reports)},
Year={2023}
}


2022

Sequential Brick Assembly with Efficient Constraint Satisfaction

Seokjun Ahn, Jungtaek Kim, Minsu Cho, and Jaesik Park. 2210.01021 (arXiv), 2022

Paper

@article{Ahn_Sequential_arXiv_2022,
Title={Sequential Brick Assembly with Efficient Constraint Satisfaction},
Author={Seokjun Ahn and Jungtaek Kim and Minsu Cho and Jaesik Park},
Journal={2210.01021 (arXiv)},
Year={2022}
}

LaplacianFusion: Detailed 3D Clothed-Human Body Reconstruction

Hyomin Kim, Hyeonseo Nam, Jungeon Kim, Jaesik Park, and Seungyong Lee. ACM Special Interest Group on Graphics and Interactive Techniques (SIGGRAPH Asia), 2022
(Accepted as a journal track paper)

Paper

@inproceedings{Kim_LaplacianFusion_SIGGRAPH_Asia_2022,
Title={LaplacianFusion: Detailed 3D Clothed-Human Body Reconstruction},
Author={Hyomin Kim and Hyeonseo Nam and Jungeon Kim and Jaesik Park and Seungyong Lee},
Booktitle={Proceedings of the ACM Special Interest Group on Graphics and Interactive Techniques (SIGGRAPH Asia)},
Year={2022}
}

PeRFception: Perception using Radiance Fields

Yoonwoo Jeong*, Seungjoo Shin*, Junha Lee*, Christopher Choy, Animashree Anandkumar, Minsu Cho, and Jaesik Park. Conf. on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, 2022
(*Equal contribution)
StarFork

Project Page Paper Code

@inproceedings{Jeong_PeRFception_NeurIPS_2022,
Title={PeRFception: Perception using Radiance Fields},
Author={Yoonwoo Jeong and Seungjoo Shin and Junha Lee and Christopher Choy and Animashree Anandkumar and Minsu Cho and Jaesik Park},
Booktitle={Proceedings of the Conf. on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track},
Year={2022}
}

Learning Debiased Classifier with Biased Committee

Nayeong Kim, Sehyun Hwang, Sungsoo Ahn, Jaesik Park, and Suha Kwak. Conf. on Neural Information Processing Systems (NeurIPS), 2022

Paper

@inproceedings{Kim_Learning_NeurIPS_2022,
Title={Learning Debiased Classifier with Biased Committee},
Author={Nayeong Kim and Sehyun Hwang and Sungsoo Ahn and Jaesik Park and Suha Kwak},
Booktitle={Proceedings of the Conf. on Neural Information Processing Systems (NeurIPS)},
Year={2022}
}

A Rotated Hyperbolic Wrapped Normal Distribution for Hierarchical Representation Learning

Seunghyuk Cho, Juyong Lee, Jaesik Park, and Dongwoo Kim. Conf. on Neural Information Processing Systems (NeurIPS), 2022

Paper

@inproceedings{Cho_A_NeurIPS_2022,
Title={A Rotated Hyperbolic Wrapped Normal Distribution for Hierarchical Representation Learning},
Author={Seunghyuk Cho and Juyong Lee and Jaesik Park and Dongwoo Kim},
Booktitle={Proceedings of the Conf. on Neural Information Processing Systems (NeurIPS)},
Year={2022}
}

SeLCA: Self-Supervised Learning of Canonical Axis

Seungwook Kim, Yoonwoo Jeong, Chunghyun Park, Jaesik Park, and Minsu Cho. Symmetry and Geometry in Neural Representations (NeurReps), NeurIPS workshop, 2022

@inproceedings{Kim_SeLCA_NeurReps_2022,
Title={SeLCA: Self-Supervised Learning of Canonical Axis},
Author={Seungwook Kim and Yoonwoo Jeong and Chunghyun Park and Jaesik Park and Minsu Cho},
Booktitle={Proceedings of the Symmetry and Geometry in Neural Representations (NeurReps), NeurIPS workshop},
Year={2022}
}

Substructure-Atom Cross Attention for Molecular Representation Learning

Jiye Kim, Seungbeom Lee, Dongwoo Kim, Sungsoo Ahn, and Jaesik Park. AI for Science: Progress and Promises (AI4Science) NeurIPS workshop, 2022

Paper

@inproceedings{Kim_SubstructureAtom_AI4Science_2022,
Title={Substructure-Atom Cross Attention for Molecular Representation Learning},
Author={Jiye Kim and Seungbeom Lee and Dongwoo Kim and Sungsoo Ahn and Jaesik Park},
Booktitle={Proceedings of the AI for Science: Progress and Promises (AI4Science) NeurIPS workshop},
Year={2022}
}

Style-Agnostic Reinforcement Learning

Juyong Lee*, Seokjun Ahn*, and Jaesik Park. European Conf. on Computer Vision (ECCV), 2022
(*Equal contribution)

Paper Code

@inproceedings{Lee_StyleAgnostic_ECCV_2022,
Title={Style-Agnostic Reinforcement Learning},
Author={Juyong Lee and Seokjun Ahn and Jaesik Park},
Booktitle={Proceedings of the European Conf. on Computer Vision (ECCV)},
Year={2022}
}

PointMixer: MLP-Mixer for Point Cloud Understanding

Jaesung Choe*, Chunghyun Park*, Francois Rameau, Jaesik Park, and In So Kweon. European Conf. on Computer Vision (ECCV), 2022
(*Equal contribution)

Paper Code

@inproceedings{Choe_PointMixer_ECCV_2022,
Title={PointMixer: MLP-Mixer for Point Cloud Understanding},
Author={Jaesung Choe and Chunghyun Park and Francois Rameau and Jaesik Park and In So Kweon},
Booktitle={Proceedings of the European Conf. on Computer Vision (ECCV)},
Year={2022}
}

CostDCNet: Cost Volume based Depth Completion for a Single RGB-D Image

Jaewon Kam, Jungeon Kim, Soongjin Kim, Jaesik Park, and Seungyong Lee. European Conf. on Computer Vision (ECCV), 2022

Paper Code

@inproceedings{Kam_CostDCNet_ECCV_2022,
Title={CostDCNet: Cost Volume based Depth Completion for a Single RGB-D Image},
Author={Jaewon Kam and Jungeon Kim and Soongjin Kim and Jaesik Park and Seungyong Lee},
Booktitle={Proceedings of the European Conf. on Computer Vision (ECCV)},
Year={2022}
}

Learning to Assemble Geometric Shapes

Jinhwi Lee, Jungtaek Kim, Hyunsoo Chung, Jaesik Park, and Minsu Cho. Int. Joint Conf. on Artificial Intelligence (IJCAI), 2022

Paper

@inproceedings{Lee_Learning_IJCAI_2022,
Title={Learning to Assemble Geometric Shapes},
Author={Jinhwi Lee and Jungtaek Kim and Hyunsoo Chung and Jaesik Park and Minsu Cho},
Booktitle={Proceedings of the Int. Joint Conf. on Artificial Intelligence (IJCAI)},
Year={2022}
}

Instance-wise Occlusion and Depth Orders in Natural Scenes

Hyunmin Lee and Jaesik Park. Int. Conf. on Computer Vision and Pattern Recognition (CVPR), 2022

Paper Code

@inproceedings{Lee_Instancewise_CVPR_2022,
Title={Instance-wise Occlusion and Depth Orders in Natural Scenes},
Author={Hyunmin Lee and Jaesik Park},
Booktitle={Proceedings of the Int. Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2022}
}

Fast Point Transformer

Chunghyun Park, Yoonwoo Jeong, Minsu Cho, and Jaesik Park. Int. Conf. on Computer Vision and Pattern Recognition (CVPR), 2022
StarFork

Project Page Paper Code

@inproceedings{Park_Fast_CVPR_2022,
Title={Fast Point Transformer},
Author={Chunghyun Park and Yoonwoo Jeong and Minsu Cho and Jaesik Park},
Booktitle={Proceedings of the Int. Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2022}
}

3D Scene Painting via Semantic Image Synthesis

Jaebong Jeong, Janghun Jo, Sunghyun Cho, and Jaesik Park. Int. Conf. on Computer Vision and Pattern Recognition (CVPR), 2022

Project Page Paper

@inproceedings{Jeong_3D_CVPR_2022,
Title={3D Scene Painting via Semantic Image Synthesis},
Author={Jaebong Jeong and Janghun Jo and Sunghyun Cho and Jaesik Park},
Booktitle={Proceedings of the Int. Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2022}
}

TextureMe: High-quality Textured Scene Reconstruction in Real-time

Jungeon Kim, Hyomin Kim, Hyeonseo Nam, Jaesik Park, and Seungyong Lee. ACM Transactions on Graphics (ToG), 2022
(also presented at SIGGRAPH2022)

Paper

@article{Kim_TextureMe_ToG_2022,
Title={TextureMe: High-quality Textured Scene Reconstruction in Real-time},
Author={Jungeon Kim and Hyomin Kim and Hyeonseo Nam and Jaesik Park and Seungyong Lee},
Journal={ACM Transactions on Graphics (ToG)},
Year={2022}
}

Deep Point Cloud Reconstruction

Jaesung Choe, Byeongin Joung, Francois Rameau, Jaesik Park, and In So Kweon. Int. Conf. on Learning Representations (ICLR), 2022

Paper

@inproceedings{Choe_Deep_ICLR_2022,
Title={Deep Point Cloud Reconstruction},
Author={Jaesung Choe and Byeongin Joung and Francois Rameau and Jaesik Park and In So Kweon},
Booktitle={Proceedings of the Int. Conf. on Learning Representations (ICLR)},
Year={2022}
}


2021

HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challenge

Jae Shin Yoon, Zhixuan Yu, Jaesik Park, and Hyun Soo Park. Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021

Project Page Paper

@article{Yoon_HUMBI_TPAMI_2021,
Title={HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challenge},
Author={Jae Shin Yoon and Zhixuan Yu and Jaesik Park and Hyun Soo Park},
Journal={Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
Year={2021}
}

Putting 3D Spatially Sparse Networks on a Diet

Junha Lee, Christopher Choy, and Jaesik Park. 2112.01316 (arXiv), 2021

Paper

@article{Lee_Putting_arXiv_2021,
Title={Putting 3D Spatially Sparse Networks on a Diet},
Author={Junha Lee and Christopher Choy and Jaesik Park},
Journal={2112.01316 (arXiv)},
Year={2021}
}

Revisiting LiDAR Registration and Reconstruction: A Range Image Perspective

Wei Dong*, Kwonyoung Ryu*, Michael Kaess, and Jaesik Park. 2112.02779 (arXiv), 2021
(*Equal contribution)

Paper

@article{Dong_Revisiting_arXiv_2021,
Title={Revisiting LiDAR Registration and Reconstruction: A Range Image Perspective},
Author={Wei Dong and Kwonyoung Ryu and Michael Kaess and Jaesik Park},
Journal={2112.02779 (arXiv)},
Year={2021}
}

Self-Supervised Real-time Video Stabilization

Jinsoo Choi, Jaesik Park, and In So Kweon. British Machine Vision Conference (BMVC), 2021

Paper

@inproceedings{Choi_SelfSupervised_BMVC_2021,
Title={Self-Supervised Real-time Video Stabilization},
Author={Jinsoo Choi and Jaesik Park and In So Kweon},
Booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
Year={2021}
}

Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training

Minguk Kang, Woohyeon Shim, Minsu Cho, and Jaesik Park. Conf. on Neural Information Processing Systems (NeurIPS), 2021

Paper Code

@inproceedings{Kang_Rebooting_NeurIPS_2021,
Title={Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training},
Author={Minguk Kang and Woohyeon Shim and Minsu Cho and Jaesik Park},
Booktitle={Proceedings of the Conf. on Neural Information Processing Systems (NeurIPS)},
Year={2021}
}

Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning

Hyunsoo Chung, Jungtaek Kim, Boris Knyazev, Jinhwi Lee, Graham W. Taylor, Jaesik Park, and Minsu Cho. Conf. on Neural Information Processing Systems (NeurIPS), 2021

Paper

@inproceedings{Chung_BrickbyBrick_NeurIPS_2021,
Title={Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning},
Author={Hyunsoo Chung and Jungtaek Kim and Boris Knyazev and Jinhwi Lee and Graham W. Taylor and Jaesik Park and Minsu Cho},
Booktitle={Proceedings of the Conf. on Neural Information Processing Systems (NeurIPS)},
Year={2021}
}

Self-Calibrating Neural Radiance Fields

Yoonwoo Jeong, Seokjun Ahn, Christopher Choy, Animashree Anandkumar, Minsu Cho, and Jaesik Park. Int. Conf. on Computer Vision (ICCV), 2021
StarFork

Project Page Paper Code

@inproceedings{Jeong_SelfCalibrating_ICCV_2021,
Title={Self-Calibrating Neural Radiance Fields},
Author={Yoonwoo Jeong and Seokjun Ahn and Christopher Choy and Animashree Anandkumar and Minsu Cho and Jaesik Park},
Booktitle={Proceedings of the Int. Conf. on Computer Vision (ICCV)},
Year={2021}
}

Deep Hough Voting for Robust Global Registration

Junha Lee, Seungwook Kim, Minsu Cho, and Jaesik Park. Int. Conf. on Computer Vision (ICCV), 2021

Project Page Paper Supplement Code

@inproceedings{Lee_Deep_ICCV_2021,
Title={Deep Hough Voting for Robust Global Registration},
Author={Junha Lee and Seungwook Kim and Minsu Cho and Jaesik Park},
Booktitle={Proceedings of the Int. Conf. on Computer Vision (ICCV)},
Year={2021}
}

Deep Virtual Markers for Articulated 3D Shapes

Hyomin Kim, Jungeon Kim, Jaewon Kam, Jaesik Park*, and Seungyong Lee*. Int. Conf. on Computer Vision (ICCV), 2021
(*Joint corrresponding authors, Oral Presentation, 3.4% acceptance rate)

Paper Code

@inproceedings{Kim_Deep_ICCV_2021,
Title={Deep Virtual Markers for Articulated 3D Shapes},
Author={Hyomin Kim and Jungeon Kim and Jaewon Kam and Jaesik Park and Seungyong Lee*},
Booktitle={Proceedings of the Int. Conf. on Computer Vision (ICCV)},
Year={2021}
}

STAD: Stable Video Depth Estimation

Hyunmin Lee and Jaesik Park. IEEE Int. Conf. on Image Processing (ICIP), 2021

Paper Code

@inproceedings{Lee_STAD_ICIP_2021,
Title={STAD: Stable Video Depth Estimation},
Author={Hyunmin Lee and Jaesik Park},
Booktitle={Proceedings of the IEEE Int. Conf. on Image Processing (ICIP)},
Year={2021}
}

Accelerated Crystal Structure Prediction of Multi-elements Random Alloy using Expandable Features

Taewon Jin, Taesoo Park, Ina Park, Jaesik Park*, and Ji Hoon Shim*. published by Nature Research (Scientific Reports), 2021
(*Joint corrresponding authors)

Paper

@article{Jin_Accelerated_Scientific_Reports_2021,
Title={Accelerated Crystal Structure Prediction of Multi-elements Random Alloy using Expandable Features},
Author={Taewon Jin and Taesoo Park and Ina Park and Jaesik Park and Ji Hoon Shim*},
Journal={published by Nature Research (Scientific Reports)},
Volume={5194},
Number={11},
Year={2021}
}

Spatiotemporal Texture Reconstruction for Dynamic Objects Using a Single RGB-D Camera

Hyomin Kim, Jungeon Kim, Hyeonseo Nam, Jaesik Park, and Seungyong Lee. 42nd Annual Conference of the European Association for Computer Graphics (EuroGraphics), 2021

Paper

@inproceedings{Kim_Spatiotemporal_EuroGraphics_2021,
Title={Spatiotemporal Texture Reconstruction for Dynamic Objects Using a Single RGB-D Camera},
Author={Hyomin Kim and Jungeon Kim and Hyeonseo Nam and Jaesik Park and Seungyong Lee},
Booktitle={Proceedings of the 42nd Annual Conference of the European Association for Computer Graphics (EuroGraphics)},
Year={2021}
}

High-quality Frame Interpolation via Tridirectional Inference

Jinsoo Choi, Jaesik Park, and In So Kweon. Winter Conf. on Applications of Computer Vision (WACV), 2021

Paper Code

@inproceedings{Choi_Highquality_WACV_2021,
Title={High-quality Frame Interpolation via Tridirectional Inference},
Author={Jinsoo Choi and Jaesik Park and In So Kweon},
Booktitle={Proceedings of the Winter Conf. on Applications of Computer Vision (WACV)},
Year={2021}
}


2020

ContraGAN: Contrastive Learning for Conditional Image Generation

Minguk Kang and Jaesik Park. Conf. on Neural Information Processing Systems (NeurIPS), 2020

Paper Code

@inproceedings{Kang_ContraGAN_NeurIPS_2020,
Title={ContraGAN: Contrastive Learning for Conditional Image Generation},
Author={Minguk Kang and Jaesik Park},
Booktitle={Proceedings of the Conf. on Neural Information Processing Systems (NeurIPS)},
Year={2020}
}

Combinatorial 3D Shape Generation via Sequential Assembly

Jungtaek Kim, Hyunsoo Chung, Minsu Cho, and Jaesik Park. Machine Learning for Engineering Modeling, Simulation, and Design (ML4Eng), NeurIPS workshop, 2020

Paper Code

@inproceedings{Kim_Combinatorial_ML4Eng_2020,
Title={Combinatorial 3D Shape Generation via Sequential Assembly},
Author={Jungtaek Kim and Hyunsoo Chung and Minsu Cho and Jaesik Park},
Booktitle={Proceedings of the Machine Learning for Engineering Modeling, Simulation, and Design (ML4Eng), NeurIPS workshop},
Year={2020}
}

Fragment Relation Networks for Geometric Shape Assembly

Jinhwi Lee*, Jungtaek Kim*, Hyunsoo Chung, Jaesik Park, and Minsu Cho. Learning Meets Combinatorial Algorithms (LMCA), NeurIPS workshop, 2020
(*Equal contribution)

Paper

@inproceedings{Lee_Fragment_LMCA_2020,
Title={Fragment Relation Networks for Geometric Shape Assembly},
Author={Jinhwi Lee and Jungtaek Kim and Hyunsoo Chung and Jaesik Park and Minsu Cho},
Booktitle={Proceedings of the Learning Meets Combinatorial Algorithms (LMCA), NeurIPS workshop},
Year={2020}
}

HUMBI: A Large Multiview Dataset of Human Body Expressions

Zhixuan Yu, Jaeshin Yoon, Inkyu Lee, Prashanth Venkatesh, Jaesik Park, Jihun Yu, and Hyunsoo Park. Conf. on Computer Vision and Pattern Recognition (CVPR), 2020

Project Page Paper Video

@inproceedings{Yu_HUMBI_CVPR_2020,
Title={HUMBI: A Large Multiview Dataset of Human Body Expressions},
Author={Zhixuan Yu and Jaeshin Yoon and Inkyu Lee and Prashanth Venkatesh and Jaesik Park and Jihun Yu and Hyunsoo Park},
Booktitle={Proceedings of the Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2020}
}

High-Dimensional Convolutional Networks for Geometric Pattern Recognition

Christopher Choy, Junha Lee, Rene Ranftl, Jaesik Park, and Vladlen Koltun. Conf. on Computer Vision and Pattern Recognition (CVPR), 2020
(Oral Presentation, 5.7% acceptance rate)

Paper Supplement Code

@inproceedings{Choy_HighDimensional_CVPR_2020,
Title={High-Dimensional Convolutional Networks for Geometric Pattern Recognition},
Author={Christopher Choy and Junha Lee and Rene Ranftl and Jaesik Park and Vladlen Koltun},
Booktitle={Proceedings of the Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2020}
}

Future Video Synthesis with Object Motion Predictions

Yue Wu, Rongrong Gao, Jaesik Park, and Qifeng Chen. Conf. on Computer Vision and Pattern Recognition (CVPR), 2020

Paper Supplement Code Video

@inproceedings{Wu_Future_CVPR_2020,
Title={Future Video Synthesis with Object Motion Predictions},
Author={Yue Wu and Rongrong Gao and Jaesik Park and Qifeng Chen},
Booktitle={Proceedings of the Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2020}
}


2019

Fully Convolutional Geometric Features

Christopher Choy*, Jaesik Park*, and Vladlen Koltun. Int. Conf. on Computer Vision (ICCV), 2019
(*Equal contribution)

Paper Code

@inproceedings{Choy_Fully_ICCV_2019,
Title={Fully Convolutional Geometric Features},
Author={Christopher Choy and Jaesik Park and Vladlen Koltun},
Booktitle={Proceedings of the Int. Conf. on Computer Vision (ICCV)},
Year={2019}
}

Global Texture Mapping for Dynamic Objects

Jungeon Kim, Hyomin Kim, Jaesik Park, and Seungyong Lee. Pacific Graphics (PG), 2019

Paper

@article{Kim_Global_PG_2019,
Title={Global Texture Mapping for Dynamic Objects},
Author={Jungeon Kim and Hyomin Kim and Jaesik Park and Seungyong Lee},
Journal={Pacific Graphics (PG)},
Volume={38},
Number={7},
Pages={697-705},
Year={2019}
}

GPU Accelerated Robust Scene Reconstruction

Wei Dong, Jaesik Park, Yi Yang, and Michael Kaess. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), 2019

Paper Video

@inproceedings{Dong_GPU_IROS_2019,
Title={GPU Accelerated Robust Scene Reconstruction},
Author={Wei Dong and Jaesik Park and Yi Yang and Michael Kaess},
Booktitle={Proceedings of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS)},
Year={2019}
}

Depth from a Light Field Image with Learning-based Matching Costs

Hae-Gon Jeon, Jaesik Park, Gyeongmin Choe, Jinsun Park, Yunsu Bok, Yu-Wing Tai, and In So Kweon. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019

Paper

@article{Jeon_Depth_TPAMI_2019,
Title={Depth from a Light Field Image with Learning-based Matching Costs},
Author={Hae-Gon Jeon and Jaesik Park and Gyeongmin Choe and Jinsun Park and Yunsu Bok and Yu-Wing Tai and In So Kweon},
Journal={IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
Volume={41},
Number={2},
Pages={297-310},
Year={2019}
}


2018

Tangent Convolutions for Dense Prediction in 3D

Maxim Tatarchenko*, Jaesik Park*, Vladlen Koltun, and Qian-Yi Zhou. Conf. on Computer Vision and Pattern Recognition (CVPR), 2018
(*Equal contribution. Spotlight Oral Presentation)

Project Page Paper Code

@inproceedings{Tatarchenko_Tangent_CVPR_2018,
Title={Tangent Convolutions for Dense Prediction in 3D},
Author={Maxim Tatarchenko and Jaesik Park and Vladlen Koltun and Qian-Yi Zhou},
Booktitle={Proceedings of the Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2018}
}

Open3D: A Modern Library For 3D Data Processing

Qian-Yi Zhou, Jaesik Park, and Vladlen Koltun. 1801.09847 (arXiv), 2018
StarFork

Project Page Paper Code Video Tutorial

@article{Zhou_Open3D_arXiv_2018,
Title={Open3D: A Modern Library For 3D Data Processing},
Author={Qian-Yi Zhou and Jaesik Park and Vladlen Koltun},
Journal={1801.09847 (arXiv)},
Year={2018}
}

Real-time Head Pose Estimation using Multi-task Deep Neural Network

Byungtae Ahn, Dong-Geol Choi, Jaesik Park, and In So Kweon. Robotics and Autonomous Systems (RAS), 2018

Paper

@inproceedings{Ahn_Realtime_RAS_2018,
Title={Real-time Head Pose Estimation using Multi-task Deep Neural Network},
Author={Byungtae Ahn and Dong-Geol Choi and Jaesik Park and In So Kweon},
Booktitle={Proceedings of the Robotics and Autonomous Systems (RAS)},
Year={2018}
}


2017

Colored Point Cloud Registration Revisited

Jaesik Park, Qian-Yi Zhou, and Vladlen Koltun. Int. Conf. on Computer Vision (ICCV), 2017

Project Page Supplement Code Data

@inproceedings{Park_Colored_ICCV_2017,
Title={Colored Point Cloud Registration Revisited},
Author={Jaesik Park and Qian-Yi Zhou and Vladlen Koltun},
Booktitle={Proceedings of the Int. Conf. on Computer Vision (ICCV)},
Year={2017}
}

Tanks and Temples: Benchmarking Large-Scale Scene Reconstruction

Arno Knapitsch, Jaesik Park, Qian-Yi Zhou, and Vladlen Koltun. ACM Special Interest Group on Graphics and Interactive Techniques (SIGGRAPH), 2017

Project Page Paper Code Data Video

@inproceedings{Knapitsch_Tanks_SIGGRAPH_2017,
Title={Tanks and Temples: Benchmarking Large-Scale Scene Reconstruction},
Author={Arno Knapitsch and Jaesik Park and Qian-Yi Zhou and Vladlen Koltun},
Booktitle={Proceedings of the ACM Special Interest Group on Graphics and Interactive Techniques (SIGGRAPH)},
Year={2017}
}

Refining Geometry from Depth Sensors using IR Shading Images

Gyeongmin Choe, Jaesik Park, Yu-Wing Tai, and In So Kweon. International Journal of Computer Vision (IJCV), 2017

Paper

@article{Choe_Refining_IJCV_2017,
Title={Refining Geometry from Depth Sensors using IR Shading Images},
Author={Gyeongmin Choe and Jaesik Park and Yu-Wing Tai and In So Kweon},
Journal={International Journal of Computer Vision (IJCV)},
Volume={122},
Number={1},
Pages={1-16},
Year={2017}
}

Category Specific Salient View Selection via Deep Convolutional Neural Networks

Seong heum Kim, Yu Wing Tai, Joon Young Lee, Jaesik Park, and In So Kweon. Computer Graphics Forum (CGF), 2017

Paper

@inproceedings{Kim_Category_CGF_2017,
Title={Category Specific Salient View Selection via Deep Convolutional Neural Networks},
Author={Seong heum Kim and Yu Wing Tai and Joon Young Lee and Jaesik Park and In So Kweon},
Booktitle={Proceedings of the Computer Graphics Forum (CGF)},
Year={2017}
}


2016

Robust Multiview Photometric Stereo using Planar Mesh Parameterization

Jaesik Park, Sudipta N. Sinha, Yasuyuki Matsushita, Yu-Wing Tai, and In So Kweon. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016

Project Page

@article{Park_Robust_TPAMI_2016,
Title={Robust Multiview Photometric Stereo using Planar Mesh Parameterization},
Author={Jaesik Park and Sudipta N. Sinha and Yasuyuki Matsushita and Yu-Wing Tai and In So Kweon},
Journal={IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
Volume={39},
Number={8},
Pages={1591-1604},
Year={2016}
}

Fast Global Registration

Qian-Yi Zhou, Jaesik Park, and Vladlen Koltun. European Conf. on Computer Vision (ECCV), 2016
(Oral Presentation, 1.8% acceptance rate)

Project Page Paper Code

@inproceedings{Zhou_Fast_ECCV_2016,
Title={Fast Global Registration},
Author={Qian-Yi Zhou and Jaesik Park and Vladlen Koltun},
Booktitle={Proceedings of the European Conf. on Computer Vision (ECCV)},
Year={2016}
}

Efficient and Robust Color Consistency for Community Photo Collections

Jaesik Park, Yu-Wing Tai, Sudipta N. Sinha, and In So Kweon. Conf. on Computer Vision and Pattern Recognition (CVPR), 2016

Project Page Code

@inproceedings{Park_Efficient_CVPR_2016,
Title={Efficient and Robust Color Consistency for Community Photo Collections},
Author={Jaesik Park and Yu-Wing Tai and Sudipta N. Sinha and In So Kweon},
Booktitle={Proceedings of the Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2016}
}

High-quality Depth from Uncalibrated Small Motion Clip

Hyowon Ha, Sunghoon Im, Jaesik Park, Hae-Gon Jeon, and In So Kweon. Conf. on Computer Vision and Pattern Recognition (CVPR), 2016
(Oral Presentation, 3.9% acceptance rate)

Project Page Code

@inproceedings{Ha_Highquality_CVPR_2016,
Title={High-quality Depth from Uncalibrated Small Motion Clip},
Author={Hyowon Ha and Sunghoon Im and Jaesik Park and Hae-Gon Jeon and In So Kweon},
Booktitle={Proceedings of the Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2016}
}

Vision System and Depth Processing for DRC-HUBO+

Inwook Shim, Seunghak Shin, Yunsu Bok, Kyungdon Joo, Dong-Geol Choi, Joon-Young Lee, Jaesik Park, Jun Ho Oh, and In So Kweon. IEEE Int. Conf. on Robotics and Automation (ICRA), 2016
(Depth processing algorithm of Team KAIST (winner of DARPA robotics challenge finals 2015))

Project Page Paper Supplement Data

@inproceedings{Shim_Vision_ICRA_2016,
Title={Vision System and Depth Processing for DRC-HUBO+},
Author={Inwook Shim and Seunghak Shin and Yunsu Bok and Kyungdon Joo and Dong-Geol Choi and Joon-Young Lee and Jaesik Park and Jun Ho Oh and In So Kweon},
Booktitle={Proceedings of the IEEE Int. Conf. on Robotics and Automation (ICRA)},
Year={2016}
}

Multi-view Object Extraction with Fractional Boundaries

Seong-Heum Kim, Yu-Wing Tai, Jaesik Park, and In So Kweon. IEEE Transaction on Image Processing (TIP), 2016

Paper

@article{Kim_Multiview_TIP_2016,
Title={Multi-view Object Extraction with Fractional Boundaries},
Author={Seong-Heum Kim and Yu-Wing Tai and Jaesik Park and In So Kweon},
Journal={IEEE Transaction on Image Processing (TIP)},
Volume={25},
Number={8},
Pages={3639-3654},
Year={2016}
}


2015

Dense Depth and Albedo from a Single-shot Structured Light

Hyowon Ha, Jaesik Park, and In So Kweon. Int. Conf. on 3D Vision (3DV), 2015

Paper

@inproceedings{Ha_Dense_3DV_2015,
Title={Dense Depth and Albedo from a Single-shot Structured Light},
Author={Hyowon Ha and Jaesik Park and In So Kweon},
Booktitle={Proceedings of the Int. Conf. on 3D Vision (3DV)},
Year={2015}
}

Accurate Depth Map Estimation from a Lenslet Light Field Camera

Hae-Gon Jeon, Jaesik Park, Gyeongmin Choe, Jinsun Park, Yunsu Bok, Yu-Wing Tai, and In So Kweon. Conf. on Computer Vision and Pattern Recognition (CVPR), 2015

Paper Code

@inproceedings{Jeon_Accurate_CVPR_2015,
Title={Accurate Depth Map Estimation from a Lenslet Light Field Camera},
Author={Hae-Gon Jeon and Jaesik Park and Gyeongmin Choe and Jinsun Park and Yunsu Bok and Yu-Wing Tai and In So Kweon},
Booktitle={Proceedings of the Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2015}
}

Multi-modal Pedestrian Detection: Benchmark Dataset and Baselines

SoonMin Hwang, Jaesik Park, Namil Kim, Yukyung Choi, and In So Kweon. Conf. on Computer Vision and Pattern Recognition (CVPR), 2015

Project Page

@inproceedings{Hwang_Multimodal_CVPR_2015,
Title={Multi-modal Pedestrian Detection: Benchmark Dataset and Baselines},
Author={SoonMin Hwang and Jaesik Park and Namil Kim and Yukyung Choi and In So Kweon},
Booktitle={Proceedings of the Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2015}
}


2014

High Quality Depth Map Upsampling and Completion for RGB-D Cameras

Jaesik Park, Hyeongwoo Kim, Yu-Wing Tai, Michael S. Brown, and In-So Kweon. IEEE Transaction on Image Processing (TIP), 2014

Project Page

@article{Park_High_TIP_2014,
Title={High Quality Depth Map Upsampling and Completion for RGB-D Cameras},
Author={Jaesik Park and Hyeongwoo Kim and Yu-Wing Tai and Michael S. Brown and In-So Kweon},
Journal={IEEE Transaction on Image Processing (TIP)},
Volume={23},
Number={12},
Pages={5559-5572},
Year={2014}
}

Real-time Head Orientation from a Monocular Camera using Deep Neural Network

Byungtae Ahn, Jaesik Park, and In So Kweon. Asian Conf. on Computer Vision (ACCV), 2014

Paper

@inproceedings{Ahn_Realtime_ACCV_2014,
Title={Real-time Head Orientation from a Monocular Camera using Deep Neural Network},
Author={Byungtae Ahn and Jaesik Park and In So Kweon},
Booktitle={Proceedings of the Asian Conf. on Computer Vision (ACCV)},
Year={2014}
}

GMM-based Saliency Aggregation for Calibration-free Gaze Estimation

Jinsoo Choi, Byungtae Ahn, Jaesik Park, and In So Kweon. Int. Conf. on Image Processing (ICIP), 2014

Paper

@inproceedings{Choi_GMMbased_ICIP_2014,
Title={GMM-based Saliency Aggregation for Calibration-free Gaze Estimation},
Author={Jinsoo Choi and Byungtae Ahn and Jaesik Park and In So Kweon},
Booktitle={Proceedings of the Int. Conf. on Image Processing (ICIP)},
Year={2014}
}

Exploiting Shading Cues in Kinect IR Images for Geometry Refinement

Gyeongmin Choe*, Jaesik Park*, Yu-Wing Tai, and In So Kweon. Conf. on Computer Vision and Pattern Recognition (CVPR), 2014
(*Equal contributions. Received 20th HumanTech Paper Award (Silver Prize), Samsung Electronics Corp.)

Project Page

@inproceedings{Choe_Exploiting_CVPR_2014,
Title={Exploiting Shading Cues in Kinect IR Images for Geometry Refinement},
Author={Gyeongmin Choe and Jaesik Park and Yu-Wing Tai and In So Kweon},
Booktitle={Proceedings of the Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2014}
}

Calibrating a Non-isotropic Near Point Light Source using a Plane

Jaesik Park, Sudipta N. Sinha, Yasuyuki Matsushita, Yu-Wing Tai, and In So Kweon. Conf. on Computer Vision and Pattern Recognition (CVPR), 2014

Project Page

@inproceedings{Park_Calibrating_CVPR_2014,
Title={Calibrating a Non-isotropic Near Point Light Source using a Plane},
Author={Jaesik Park and Sudipta N. Sinha and Yasuyuki Matsushita and Yu-Wing Tai and In So Kweon},
Booktitle={Proceedings of the Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2014}
}


2013

Multiview Photometric Stereo using Planar Mesh Parameterization

Jaesik Park, Sudipta N. Sinha, Yasuyuki Matsushita, Yu-Wing Tai, and In So Kweon. Int. Conf. on Computer Vision (ICCV), 2013
(Received 19th HumanTech Paper Award (Silver Prize), Samsung Electronics Corp.)

Project Page

@inproceedings{Park_Multiview_ICCV_2013,
Title={Multiview Photometric Stereo using Planar Mesh Parameterization},
Author={Jaesik Park and Sudipta N. Sinha and Yasuyuki Matsushita and Yu-Wing Tai and In So Kweon},
Booktitle={Proceedings of the Int. Conf. on Computer Vision (ICCV)},
Year={2013}
}


2012

Tensor Voting Approach for Multi-View 3D Scene-flow Estimation and Refinement

Jaesik Park, Tae Hyun Oh, Jiyoung Jung, Yu-Wing Tai, and In So Kweon. European Conf. on Computer Vision (ECCV), 2012

Paper Supplement

@inproceedings{Park_Tensor_ECCV_2012,
Title={Tensor Voting Approach for Multi-View 3D Scene-flow Estimation and Refinement},
Author={Jaesik Park and Tae Hyun Oh and Jiyoung Jung and Yu-Wing Tai and In So Kweon},
Booktitle={Proceedings of the European Conf. on Computer Vision (ECCV)},
Year={2012}
}

Modeling Photo Composition and Its Application to Photo Re-arrangement

Jaesik Park, Joon-Young Lee, Yu-Wing Tai, and In So Kweon. Int. Conf. on Image Processing (ICIP), 2012

Paper Supplement

@inproceedings{Park_Modeling_ICIP_2012,
Title={Modeling Photo Composition and Its Application to Photo Re-arrangement},
Author={Jaesik Park and Joon-Young Lee and Yu-Wing Tai and In So Kweon},
Booktitle={Proceedings of the Int. Conf. on Image Processing (ICIP)},
Year={2012}
}

Identigram/Watermark removal using cross-channel correlation

Jaesik Park, Yu-Wing Tai, and In-So Kweon. Conf. on Computer Vision and Pattern Recognition (CVPR), 2012

Project Page

@inproceedings{Park_IdentigramWatermark_CVPR_2012,
Title={Identigram/Watermark removal using cross-channel correlation},
Author={Jaesik Park and Yu-Wing Tai and In-So Kweon},
Booktitle={Proceedings of the Conf. on Computer Vision and Pattern Recognition (CVPR)},
Year={2012}
}


2011

A Novel 2.5D Pattern for Extrinsic Calibration of ToF and Camera Fusion System

Jiyoung Jung, Yekeun Jeong, Jaesik Park, Hyowon Ha, J. D. Kim, and In-So Kweon. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), 2011

Paper

@inproceedings{Jung_A_IROS_2011,
Title={A Novel 2.5D Pattern for Extrinsic Calibration of ToF and Camera Fusion System},
Author={Jiyoung Jung and Yekeun Jeong and Jaesik Park and Hyowon Ha and J. D. Kim and In-So Kweon},
Booktitle={Proceedings of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS)},
Year={2011}
}

High Quality Depth Map Upsampling for 3D-TOF Cameras

Jaesik Park*, Hyeongwoo Kim*, Yu-Wing Tai, Michael S. Brown, and In-So Kweon. Int. Conf. on Computer Vision (ICCV), 2011
(*Equal contributions)

Project Page

@inproceedings{Park_High_ICCV_2011,
Title={High Quality Depth Map Upsampling for 3D-TOF Cameras},
Author={Jaesik Park and Hyeongwoo Kim and Yu-Wing Tai and Michael S. Brown and In-So Kweon},
Booktitle={Proceedings of the Int. Conf. on Computer Vision (ICCV)},
Year={2011}
}