Unsplashed background img 1

Bio

I am a Ph.D. student in Computer Science at the University of Toronto, advised by Alec Jacobson. I am part of the Dynamic Graphics Project lab and am affiliated with the Data Sciences Institute.

In 2022, I worked at Adobe Research with Vova Kim and Noam Aigerman. In 2021, I was an intern in the NVIDIA Seattle Robotics lab, working with Dieter Fox, Adithya Murali, and Balakumar Sundaralingam.

I am interested in computer vision, computer graphics, 3D geometry, and geometric deep learning.

Prior to my Ph.D., I worked with Ming-Hsuan Yang, Jia-Bin Huang, and Yen-Yu Lin. I received a B.S. in Electrical Engineering from National Taiwan University in 2018.

New: I am looking for a research intern or a student researcher position in 2023. Please contact me if you think I am a good match.


News


Selected Publications

Breaking Bad: A Dataset for Geometric Fracture and Reassembly
Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks, 2022
Featured Paper Presentation
[Paper] [Project page] [Baseline code] [Data generation code] [Dataset] [Video] [Poster] [Slides] [Twitter]
Grasp'D: Differentiable Contact-rich Grasp Synthesis for Multi-fingered Hands
European Conference on Computer Vision (ECCV), 2022
Oral Presentation
[Paper] [Project page] [Code] [Video] [Poster] [Twitter]
Neural Motion Fields: Encoding Grasp Trajectories as Implicit Value Functions
RSS 2022 Workshop on Implicit Representations for Robotic Manipulation, 2022
Spotlight Talk
[Paper] [Video] [Slides] [Twitter]
Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
[Paper] [Project page] [Video] [Poster] [Slides] [Twitter]
Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021
RSS 2021 Workshop on Visual Learning and Reasoning for Robotics, 2021 Spotlight Talk
ICML 2021 Workshop on Human in the Loop Learning, 2021
[Paper] [Project page] [Video] [Twitter]
Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2021
[Paper] [Project page] [Code] [Slides]
Self-Attentive 3D Human Pose and Shape Estimation from Videos
Computer Vision and Image Understanding (CVIU), 2021
[Paper]
NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
European Conference on Computer Vision (ECCV), 2020
[Paper] [Project page] [GitHub] [Colab] [Highlight video] [Highlight slides] [Full video] [Full slides]
Learning to Learn in a Semi-Supervised Fashion
European Conference on Computer Vision (ECCV), 2020
[Paper]
Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond
arXiv preprint arXiv:2002.09274
[Paper]
Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification
IEEE International Conference on Computer Vision (ICCV), 2019
[Paper] [Slides] [Poster]
CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
[Paper] [Project page] [Code] [Slides] [Poster]
Learning Resolution-Invariant Deep Representations for Person Re-Identification
AAAI Conference on Artificial Intelligence (AAAI), 2019
Oral Presentation
[Paper] [Slides] [Poster]
Deep Semantic Matching with Foreground Detection and Cycle-Consistency
Asian Conference on Computer Vision (ACCV), 2018
[Paper] [Project page] [Code] [Poster]