Jia-Bin Huang

Jia-Bin Huang 

Capital One endowed Associate Professor
Department of Computer Science, University of Maryland, College Park

Research Scientist (20%)
Reality Labs, Meta

My research interests lie at the intersection of computer vision, computer graphics, and machine learning.

Research Group | Teaching | Talks | Publications | Open Office Hours

Email: jbhuang@umd.edu (primary) | jbhuang@meta.com

More about me: CV | CV of Failures | Awesome Tips | YouTube | Twitter | Threads

  • Prospective Ph.D. students starting in Fall 2024:

    • If you are not at UMD: We will be recruiting highly motivated Ph.D. students to join our lab. Please apply through the CS department and include my name as a potential advisor in your application.

    • If you are already a UMD student, please email me your CV, prior experiences, and how you would like to get involved.

    • Questions? Check out my answers to the Ph.D. Advisor Guide.

  • Prospective Visiting Students: For short-term visiting, please fill in the form here. We will contact you if there is a match.

  • Prospective Undergraduate Students at UMD: Interested in engaging with computer vision research? Please reach out via email with your CV, transcript, your level of commitment (e.g., 10-20 hours/week), and description of what types of projects you want to work on.

  • Prospective Faculty at UMD: The CS department is hiring multiple faculty! Find out more here. Please feel free to reach out if you have any questions.

  • Prospective Research Interns at Meta: We are actively recruiting Summer 2023 research interns in the Computational Photography Group at Meta. The offers will be given in a rolling basis so apply here soon!

Research Group

PhD students

Yao-Chih Lee Yiran Xu Yue Feng Yi-Ting Chen
Yao-Chih Lee Yiran Xu Yue Feng Yi-Ting Chen
Ting-Hsuan Liao Hadi Alzayer Songwei Ge Kevin Zhang
Ting-Hsuan Liao Hadi Alzayer Songwei Ge Kevin Zhang
(with David Jacobs) (with Christopher Metzler)

Undergraduate students

Elizabeth Qiu Sanjali Yadav
Elizabeth Qiu Sanjali Yadav

Alumni

Former PhD Students

Former MS/BS Students

Former Interns (as host or co-host)

Former Visiting Students

Publications

 

Recent Trends in 3D Reconstruction of General Non-Rigid Scenes
Raza Yunus, Jan Eric Lenssen, Michael Niemeyer, Yiyi Liao, Christian Rupprecht, Christian Theobalt, Gerard Pons-Moll, Jia-Bin Huang, Vladislav Golyanik, and Eddy Ilg
EUROGRAPHICS State-of-the-Art Reports 2024
[Paper (PDF)] [Project page]

 

TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion
Yu-Ying Yeh, Jia-Bin Huang, Changil Kim, Lei Xiao, Thu Nguyen-Phuoc, Numair Khan, Cheng Zhang, Manmohan Chandraker, Carl S Marshall, Zhao Dong, and Zhengqin Li
arXiv preprint 2024
[Paper (PDF)] [Project page] [Code] [Demo]

 

FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis
Feng Liang, Bichen Wu, Jialiang Wang, Licheng Yu, Kunpeng Li, Yinan Zhao, Ishan Misra, Jia-Bin Huang, Peizhao Zhang, Peter Vajda, and Diana Marculescu
arXiv preprint 2024
[Paper (PDF)] [Project page] [Code] [Demo]

 

Fast View Synthesis of Casual Videos
Yao-Chih Lee, Zhoutong Zhang, Kevin Blackburn-Matzen, Simon Niklaus, Jianming Zhang, Jia-Bin Huang, and Feng Liu
arXiv preprint 2023
[Paper (PDF)] [Project page] [Code] [Demo]

 

Seeing the World through Your Eyes
Hadi Alzayer, Kevin Zhang, Brandon Feng, Christopher Metzler, and Jia-Bin Huang
arXiv preprint 2023
[Paper (PDF)] [Project page] [Code] [Demo]

 

In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing
Yiran Xu, Zhixin Shu, Cameron Smith, Seoung Wug Oh, and Jia-Bin Huang
arXiv preprint 2023
[Paper (PDF)] [Project page] [Code] [Demo]

 

UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video
Zhi-Hao Lin, Bohan Liu, Yi-Ting Chen, David Forsyth, Jia-Bin Huang, Anand Bhattad, and Shenlong Wang
arXiv preprint 2023
[Paper (PDF)] [Project page] [Code] [Demo]

Grounded Text-to-Image Synthesis with Attention Refocusing
Quynh Phung, Songwei Ge, Jia-Bin Huang
arXiv preprint 2023
[Paper (PDF)] [Project page] [Code] [Demo]

Single-Image 3D Human Digitization with Shape-Guided Diffusion
Badour AlBahar, Shunsuke Saito, Hung-Yu Tseng, Changil Kim, Johannes Kopf, and Jia-Bin Huang
ACM SIGGRAPH Asia 2023 (Conference track)
[Paper (PDF)] [Project page] [Code] [Demo]

Visualizing Subtle Motions from Time-Varying Radiance Fields
Brandon Yushan Feng, Hadi AlZayer, Michael Rubinstein, William T. Freeman, and Jia-Bin Huang
Proceedings of International Conference on Computer Vision (ICCV), 2023
[Paper (PDF)] [Project page] [Code] [Demo]

Expressive Text-to-Image Generation with Rich Text
Songwei Ge, Taesung Park, Jun-Yan Zhu, and Jia-Bin Huang
Proceedings of International Conference on Computer Vision (ICCV), 2023
[Paper (PDF)] [Project page] [Code] [Demo]

ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Field
Yuan Li, Zhi-Hao Lin, David Forsyth, Jia-Bin Huang, and Shenlong Wang
Proceedings of International Conference on Computer Vision (ICCV), 2023
[Paper (PDF)] [Project page] [Code]

 

Dynamic Mesh-Aware Radiance Fields
Yi-Ling Qiao, Alexander Gao, Yiran Xu, Yue Feng, Jia-Bin Huang, and Ming C. Lin
Proceedings of International Conference on Computer Vision (ICCV), 2023
[Paper (PDF)] [Project page] [Code] [Demo]

 

Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models
Songwei Ge, Seungjun Nah, Guilin Liu, Tyler Poon, Andrew Tao, Bryan Catanzaro, David Jacobs, Jia-Bin Huang, Ming-Yu Liu, and Yogesh Balaji
Proceedings of International Conference on Computer Vision (ICCV), 2023
[Paper (PDF)] [Project page] [Code] [Demo]

 

Robust Omnimatte with 3D Background Modeling
Geng Lin, Chen Gao, Jia-Bin Huang, Changil Kim, Yipeng Wang, Matthias Zwicker, and Ayush Saraf,
Proceedings of International Conference on Computer Vision (ICCV), 2023
[Paper (PDF)] [Project page] [Code] [Demo]

 

Neural-PBIR Reconstruction of Shape, Material, and Illumination
Cheng Sun, Guangyan Cai, Zhengqin Li, Cheng Zhang, Carl Marshall, Jia-Bin Huang, Shuang Zhao, and Zhao Dong
Proceedings of International Conference on Computer Vision (ICCV), 2023
[Paper (PDF)] [Project page] [Code] [[ Demo]

 

Text-driven Visual Synthesis with Latent Diffusion Prior
Ting-Hsuan Liao, Songwei Ge, Yiran Xu, Yao-Chih Lee, Badour AlBahar, and Jia-Bin Huang
arXiv preprint 2023
[Paper (PDF)] [Project page] [Code] [Demo]

 

DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs
Zhixiang Wang, Yu-Lun Liu, Jia-Bin Huang, Shin'ichi Satoh, Sizhuo Ma, Gurunandan Krishnan, and Jian Wang
International Journal of Computer Vision (IJCV)
[Paper (PDF)] [Project page] [Code] [Demo]

 

Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation
Jie An, Songyang Zhang, Harry Yang, Sonal Gupta, Jia-Bin Huang, Jiebo Luo, and Xi Yin
arXiv preprint 2023
[Paper (PDF)] [Project page] [Code]

Shape-aware Text-driven Layered Video Editing
Yao-Chih Lee, Ji-Ze Genevieve Jang, Yi-Ting Chen, Elizabeth Qiu, and Jia-Bin Huang
Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[Paper (PDF)] [Project page] [Code]

Robust Dynamic Radiance Fields
Yu-Lun Liu, Chen Gao, Andreas Meuleman, Hung-Yu Tseng, Ayush Saraf, Changil Kim, Yung-Yu Chuang, Johannes Kopf, and Jia-Bin Huang
Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[Paper (PDF)] [Project page] [Code]

DC2: Dual-Camera Defocus Control by Learning to Refocus
Hadi Alzayer, Abdullah Abuolaim, Leung Chun Chan, Yang Yang, Ying Chen Lou, Jia-Bin Huang, and Abhishek Kar
Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[Paper (PDF)] [Project page] [Video] [Two Minutes Paper]

HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling
Benjamin Attal, Jia-Bin Huang, Christian Richardt, Michael Zollhoefer, Johannes Kopf, Matthew O'Toole, and Changil Kim
Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 (Highlight)
[Paper (PDF)] [Project page] [Code] [Video]

Consistent View Synthesis with Pose-Guided Diffusion Models
Hung-Yu Tseng, Qinbo Li, Changil Kim, Suhib Alsisan, Jia-Bin Huang, and Johannes Kopf
Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[Paper (PDF)] [Project page] [Video] [Code]

Progressively Optimized Local Radiance Fields for Robust View Synthesis
Andreas Meuleman, Yu-Lun Liu, Chen Gao, Jia-Bin Huang, Changil Kim, Min H. Kim, and Johannes Kopf
Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[Paper (PDF)] [Project page] [Code] [Video]

 

Learning Representational Invariances for Data-Efficient Action Recognition
Yuliang Zou, Jinwoo Choi, Qitong Wang, and Jia-Bin Huang
Computer Vision and Image Understanding (CVIU), 2022
[Paper (PDF)] [Project page] [Code] [Supp]

Temporally Consistent Semantic Video Editing
Yiran Xu, Badour AlBahar, and Jia-Bin Huang
Proceedings of European Conference on Computer Vision (ECCV), 2022
[Paper (PDF)] [Project page] [Code]

 

Learning Instance-Specific Adaptation for Cross-Domain Segmentation
Yuliang Zou, Zizhao Zhang, Chun-Liang Li, Han Zhang, Tomas Pfister, and Jia-Bin Huang
Proceedings of European Conference on Computer Vision (ECCV), 2022
[Paper (PDF)] [Project page] [Code]

Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
Songwei Ge, Thomas Hayes, Harry Yang, Xi Yin, Guan Pang, David Jacobs, Jia-Bin Huang, and Devi Parikh
Proceedings of European Conference on Computer Vision (ECCV), 2022
[Paper (PDF)] [Project page] [Code]

 

Boosting View Synthesis with Residual Transfer
Xuejian Rong, Jia-Bin Huang, Ayush Saraf, Xuejian Rong, Ayush Saraf, Changil Kim, and Johannes Kopf
Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
[Paper (PDF)] [Project page]

Learning Neural Light Fields with Ray-Space Embedding Networks
Benjamin Attal, Jia-Bin Huang, Michael Zollhöfer, Johannes Kopf, and Changil Kim
Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
[Paper (PDF)] [Project page] [Code]

 

Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera with Global Reset Feature
Zhixiang Wang, Xiang Ji, Jia-Bin Huang, Shin'ichi Satoh, Xiao Zhou, and Yinqiang Zheng
Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
[Paper (PDF)] [Project page] [Dataset]

Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors
Qi Mao, Hsin-Ying Lee, Hung-Yu Tseng, Jia-Bin Huang, Siwei Ma, and Ming-Hsuan Yang
International Journal of Computer Vision (IJCV), 2022
[Paper (PDF)] [Project page] [Code]

Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN
Badour AlBahar, Jingwan (Cynthia) Lu, Jimei Yang, Zhixin Shu, Eli Shechtman, and Jia-Bin Huang
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia), 2021
[Paper (PDF)] [Project page] [Code] [Colab notebook]

Modulating StyleGAN for photorealistic human reposing and virtual try-on.

Learning to See Through Obstructions with Layered Decomposition
Yu-Lun Liu, Wei-Sheng Lai, Ming-Hsuan Yang, Yung-Yu Chuang, and Jia-Bin Huang
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2021
[Paper (PDF)] [Project page] [Code] [Colab notebook]
News coverage: [New Scientists]



Using meta-learning to enable faster layered decomposition with test-time optimization.

 

AMICO: Amodal Instance Composition
Peiye Zhuang, Jia-Bin Huang, Ayush Saraf, Xuejian Rong, Changil Kim, Denis Demandolx
Proceedings of British Machine Vision Conference (BMVC), 2021
[Paper (PDF)]

Dynamic View Synthesis from Dynamic Monocular Video
Chen Gao, Ayush Saraf, Johannes Kopf, and Jia-Bin Huang
[Paper (PDF)] [Project page] [Code]
Proceedings of International Conference on Computer Vision (ICCV), 2021


Regularizing scene flow and depth to disabmiguate learning space-time neural radiance field.

Hybrid Neural Fusion for Full-frame Video Stabilization
Yu-Lun Liu, Wei-Sheng Lai, Ming-Hsuan Yang, Yung-Yu Chuang, and Jia-Bin Huang
[Paper (PDF)] [Project page] [Code] [Colab notebook] [Two minute video]
Proceedings of International Conference on Computer Vision (ICCV), 2021


Warping and fusing multiple frames stabilize shaky videos without cropping.

 

Automated Movement Assessment in Stroke Rehabilitation
Tamim Ahmed, Kowshik Thopalli, Thanassis Rikakis, Pavan Turaga, Aisling Kelliher, Jia-Bin Huang, and Steven L. Wolf
Frontiers in Neurology 2021
[Paper (PDF)]

Robust Consistent Video Depth Estimation
Johannes Kopf, Xuejian Rong and Jia-Bin Huang
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 (Oral Presentation)
[Paper (PDF)] [Project page] [Code] [Colab]


Estimating geometrically consistent depth and camera poses from casually captured videos.

Space-time Neural Irradiance Fields for Free-Viewpoint Video
Wenqi Xian, Jia-Bin Huang, Johannes Kopf, and Changil Kim
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
[Paper (PDF)] [Project page] [Code]


Learning spatiotemporal NeRF for dynamic scenes from a single video is ambiguious, but we can constrain the disambiute it using scene depth.

 

PseudoSeg: Designing Pseudo Labels for Semantic Segmentation
Yuliang Zou, Zizhao Zhang, Han Zhang, Chun-Liang Li, Xiao Bian, Jia-Bin Huang, Tomas Pfister
International Conference on Learning Representations (ICLR), 2021
[Paper (PDF)] [Project page] [Code]

 

DropLoss for Long-Tail Instance Segmentation
Ting-I Hsieh*, Esther Robb*, Hwann-Tzong Chen, and Jia-Bin Huang
Proceedings of AAAI Conference on Artificial Intelligence (AAAI), 2021
[Paper (PDF)] [Project page] [Code]

Flow-edge Guided Video Completion
Chen Gao, Ayush Saraf, Jia-Bin Huang, and Johannes Kopf
Proceedings of European Conference on Computer Vision (ECCV), 2020
[Paper (PDF)] [Project page] [Code] [Colab notebook] [Two minute video]
News coverage: [New Scientists] [Syned Review]

Semantic View Synthesis
Hsin-Ping Huang, Hung-Yu Tseng, Hsin-Ying Lee, and Jia-Bin Huang
Proceedings of European Conference on Computer Vision (ECCV), 2020
[Paper (PDF)] [Project page] [Code] [Colab notebook]

DRG: Dual Relation Graph for Human-Object Interaction Detection
Chen Gao, Jiarui Xu, Yuliang Zou, and Jia-Bin Huang
Proceedings of European Conference on Computer Vision (ECCV), 2020
[Paper (PDF)] [Project page] [Code] [Colab notebook]

NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
Yun-Chun Chen*, Chen Gao*, Esther Robb, and Jia-Bin Huang
Proceedings of European Conference on Computer Vision (ECCV), 2020
[Paper (PDF)] [Project page] [Code] [Colab notebook]

 

FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning
Chia-Wen Kuo, Chih-Yao Ma, Jia-Bin Huang, and Zsolt Kira
Proceedings of European Conference on Computer Vision (ECCV), 2020
[Paper (PDF)] [Project page] [Code] [Colab notebook] (Coming soon)

 

Shuffle and Attend: Video Domain Adaptation
Jinwoo Choi, Gaurav Sharma, Samuel Schulter, and Jia-Bin Huang
Proceedings of European Conference on Computer Vision (ECCV), 2020
[Paper (PDF)] [Project page] [Code] [Colab notebook]

Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling
Yuliang Zou, Pan Ji, Quoc-Huy Tran, Jia-Bin Huang, and Manmohan Chandraker
Proceedings of European Conference on Computer Vision (ECCV), 2020
[Paper (PDF)] [Project page] [Code] [Colab notebook]

Consistent Video Depth Estimation
Xuan Luo, Jia-Bin Huang, Richard Szeliski, Kevin Matzen, and Johannes Kopf
ACM Transactions on Graphics (Proceedings of SIGGRAPH), 2020
[Paper (PDF)] [Project page] [Video] [Code] [Colab notebook] [Two minute video]

3D Photography using Context-aware Layered Depth Inpainting
Meng-Li Shih, Shih-Yang Su, Johannes Kopf, and Jia-Bin Huang
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
[Paper (PDF)] [Project page] [Code] [Colab notebook] [Two minute video]
News coverage: [Synced] [Gigazine] [Digital Information World]

Learning to See Through Obstructions
Yu-Lun Liu, Wei-Sheng Lai, Ming-Hsuan Yang, Yung-Yu Chuang, and Jia-Bin Huang
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
[Paper (PDF)] [Project page] [Code] [Colab notebook] [Two minute video]
News coverage: [New Scientists]

Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
Yu-Lun Liu*, Wei-Sheng Lai*, Yu-Sheng Chen, Yi-Lung Kao, Ming-Hsuan Yang, Yung-Yu Chuang, and Jia-Bin Huang
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
[Paper (PDF)] [Project page] [Code] [Colab notebook]

Instance-aware Image Colorization
Jheng-Wei Su, Hung-Kuo Chu, and Jia-Bin Huang
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
[Paper (PDF)] [Project page] [Code] [Colab notebook] [Two minute video]

 

Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation
Hung-Yu Tseng, Hsin-Ying Lee, Jia-Bin Huang, and Ming-Hsuan Yang
Proceedings of International Conference on Learning Representations (ICLR), 2020 (Spotlight Oral Presentation)
[Paper (PDF)] [Project page] [Code]

Unsupervised and Semi-Supervised Domain Adaptation for Action Recognition from Drones
Jinwoo Choi, Gaurav Sharma, Manmohan Chandraker, and Jia-Bin Huang
Proceedings of Winter Conference on Applications of Computer Vision (WACV), 2020
[Paper (PDF)] [Dataset] [Poster] [Slides]

 

Reducing Footskate in Human Motion Reconstruction with Ground Contact Constraints
Yuliang Zou, Jimei Yang, Duygu Ceylan, Jianming Zhang, Federico Perazzi, and Jia-Bin Huang
Proceedings of Winter Conference on Applications of Computer Vision (WACV), 2020
[Paper (PDF)] [Project page] [Code] [Poster] [Slides]

 

Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-segmentation
Yun-Chun Chen, Yen-Yu Lin, Ming-Hsuan Yang, and Jia-Bin Huang
IEEE Transactions on Pattern Recognition and Machine Intelligence (PAMI), 2020
[Paper (PDF)] [Project page] [Code]

 

DRIT++: Diverse Image-to-Image Translation via Disentangled Representations
Hsin-Ying Lee*, Hung-Yu Tseng*, Qi Mao* Jia-Bin Huang, Yu-Ding Lu, Maneesh Singh, Ming-Hsuan Yang
International Journal of Computer Vision (IJCV), 2020
[Paper (PDF)] [Project page] [Code]

 

Tracking Persons-of-Interest via Unsupervised Representation Adaptation
Shun Zhang, Jia-Bin Huang, Jongwoo Lim, Yihong Gong, Jinjun Wang, Narendra Ahuja, and Ming-Hsuan Yang
International Journal of Computer Vision (IJCV), 2020
[Paper (PDF)] [Project page] [Code]

Portrait Neural Radiance Fields from a Single Image
Chen Gao, Yichang Shih, Wei-Sheng Lai, Chia-Kai Liang, and Jia-Bin Huang
[Paper (PDF)] [Project page] arXiv 2020


Using meta-learning and 3D morphable models enables estimating portrait NeRF from a single image.

Few-shot Adaptation of Generative Adversarial Networks
Esther Robb, Vincent Chu, Abhishek Kumar Jia-Bin Huang
arXiv 2020
[Paper (PDF)] [Project page] [Code]


 

Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition
Jinwoo Choi, Chen Gao, Joseph Messou, and Jia-Bin Huang
Proceedings of Neural Information Processing Systems (NeurIPS), 2019
[Paper (PDF)] [Project page] [Code] [Poster]

 

Guided Image-to-Image Translation with Bi-Directional Feature Transformation
Badour AlBahar and Jia-Bin Huang
Proceedings of IEEE International Conference on Computer Vision (ICCV), 2019
[Paper (PDF)] [Project page] [Code] [Supp] [Poster]

 

CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency
Yun-Chun Chen, Yen-Yu Lin, Ming-Hsuan Yang, and Jia-Bin Huang
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
[Paper (PDF)] [Project page] [Code] [Poster]

SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation - A Synthetic Dataset and Baselines
Yuan-Ting Hu, Hong-Shuo Chen, Kexin Hui, Jia-Bin Huang, and Alexander Schwing
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
[Paper (PDF)] [Project page] [Code] [Poster]

 

A Closer Look at Few-shot Classification
Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, and Jia-Bin Huang
International Conference on Learning Representation (ICLR) 2019
[Paper (PDF)] [Project page] [Code] [Poster]

 

Connecting the Digital and Physical World: Improving the Robustness of Adversarial Attacks
Steve T. K. Jan, Joseph Messou, Yen-Chen Lin, Jia-Bin Huang, and Gang Wang
Proceedings of AAAI Conference on Artificial Intelligence (AAAI) 2019
[Paper (PDF)] [Project page] [Code]

 

Deep Paper Gestalt
Jia-Bin Huang
arXiv:1812.08775, 2018
Secret Proceedings of Computer Vision and Pattern Recognition (s-CVPR), 2019
[Paper (PDF)] [Project page] [Code]
News coverage: [Syncreview] [ZDNet]


 

Source Form: An Automated Crowdsourced Object Generator
Sam Blanchard, Jia-Bin Huang, Christopher B. Williams, Viswanath Meenakshisundaram, Joseph Kubalak, and Sanket Lokegaonkar
ACM SIGGRAPH Studio 2019
[Paper (PDF)] [Video]
News coverage: [3D Printing Industry] [Wherrelz]

 

Progressive Representation Adaptation for Weakly Supervised Object Localization
Dong Li, Jia-Bin Huang, Yali Li, Shengjin Wang, and Ming-Hsuan Yang
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2019
[Paper (PDF)] [Project page] [Code]

 

Joint Image Filtering with Deep Convolutional Networks
Yijun Li, Jia-Bin Huang, Narendra Ahuja, and Ming-Hsuan Yang
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2019
[Paper (PDF)] [Project page] [Code]

Multi-view Wire Art
Kai-Wen Hsiao, Jia-Bin Huang, and Hung-Kuo Chu
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia), 2018 (Oral Presentation)
[Paper (PDF)] [Project page] [Code]

 

Diverse Image-to-Image Translation via Disentangled Representations
Hsin-Ying Lee*, Hung-Yu Tseng*, Jia-Bin Huang, Maneesh Singh, Ming-Hsuan Yang
Proceedings of European Conference on Computer Vision (ECCV), 2018 (Oral Presentation)
[Paper (PDF)] [Project page] [Code] [Slides] [Poster]

 

DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency
Yuliang Zou, Zelun Luo, and Jia-Bin Huang
Proceedings of European Conference on Computer Vision (ECCV), 2018
[Paper (PDF)] [Project page] [Code] [Poster]

Learning Blind Video Temporal Consistency
Wei-Sheng Lai, Jia-Bin Huang, Oliver Wang, Eli Shechtman, Ersin Yumer, Ming-Hsuan Yang
Proceedings of European Conference on Computer Vision (ECCV), 2018
[Paper (PDF)] [Project page] [Code] [Poster] [Supp]

VideoMatch: Matching based Video Object Segmentation
Yuan-Ting Hu, Jia-Bin Huang, and Alexander Schwing
Proceedings of European Conference on Computer Vision (ECCV), 2018
[Paper (PDF)] [Project page] [Poster]

Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation
Yuan-Ting Hu, Jia-Bin Huang, and Alexander Schwing
Proceedings of European Conference on Computer Vision (ECCV), 2018
[Paper (PDF)] [Project page] [Poster]

 

iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection
Chen Gao, Yuliang Zou, and Jia-Bin Huang
Proceedings of British Machine Vision Conference (BMVC), 2018
[Paper (PDF)] [Project page] [Code] [Poster] [Supp]

 

DeepMVS: Learning Multi-View Stereopsis
Po-Han Huang, Kevin Matzen, Johannes Kopf, Narendra Ahuja, and Jia-Bin Huang
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
[Paper (PDF)] [Project page] [Code] [Poster] [Supp]

 

Deep Semantic Matching with Foreground Detection and Cycle-Consistency
Yun-Chun Chen, Po-Hsiang Huang, Li-Yu Yu, Jia-Bin Huang, Ming-Hsuan Yang, and Yen-Yu Lin
Asian Conference on Computer Vision (ACCV), 2018
[Paper (PDF)] [Project page] [Code] [Poster]

 

Semi-Automated Home-based Therapy for the Upper Extremity of Stroke Survivors
Thanassis Rikakis, Aisling Kelliher, Jinwoo Choi, Jia-Bin Huang, Kris Kitani, Steve Wolf, and Setor Zilevu
Pervasive Technologies Related to Assistive Environments (PETRA), 2018
[Paper (PDF)]

 

Progressive Cyber-Human Intelligence for Social Good
Thanassis Rikakis, Aisling Kelliher, Jia-Bin Huang, Hari Sundaram
ACM Interactions, 2018
[Paper (PDF)]

 

Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks
Wei-Sheng Lai, Jia-Bin Huang, Narendra Ahuja, and Ming-Hsuan Yang
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2018
[Paper (PDF)] [Project page] [Code]

 

Robust Visual Tracking via Hierarchical Convolutional Features
Chao Ma, Jia-Bin Huang, Xiaokang Yang, and Ming-Hsuan Yang
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2018
[Paper (PDF)] [Project page] [Code]

 

Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking
Chao Ma, Jia-Bin Huang, Xiaokang Yang, and Ming-Hsuan Yang
International Journal of Computer Vision (IJCV), 2018
[Paper (PDF)] [Project page] [Code]

 

Ensemble of Convolutional Neural Networks for Pose Estimation
Yuki Kawana, Norimichi Ukita, Jia-Bin Huang, and Ming-Hsuan Yang
Computer Vision and Image Understanding (CVIU), 2018
[Paper (PDF)]

 

Semi-Supervised Learning for Optical Flow with Generative Adversarial Networks
Wei-Sheng Lai, Jia-Bin Huang, and Ming-Hsuan Yang
Proceedings of Neural Information Processing Systems (NeurIPS), 2017
[Paper (PDF)] [Project page] [Code] [Poster] [Supp]

 

MaskRNN: Instance Level Video Object Segmentation
Yuan-Ting Hu, Jia-Bin Huang, and Alexander Schwing
Proceedings of Neural Information Processing Systems (NeurIPS), 2017
[Paper (PDF)] [Project page] [Code] [Poster]

 

Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight
Yen-Chen Lin, Ming-Yu Liu, Min Sun, and Jia-Bin Huang
Proceedings of Neural Information Processing Systems (NeurIPS) Workshop on Machine Deception, 2017
[Paper (PDF)] [Project page] [Code]

 

Unsupervised Representation Learning by Sorting Sequences
Hsin-Ying Lee, Jia-Bin Huang, Maneesh Singh, and Ming-Hsuan Yang
Proceedings of International Conference on Computer Vision (ICCV), 2017
[Paper (PDF)] [Project page] [Code] [Poster]

 

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution
Wei-Sheng Lai, Jia-Bin Huang, Narendra Ahuja, and Ming-Hsuan Yang
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
[Paper (PDF)] [Project page] [Code] [Poster] [Supp]

 

HOMER: an interactive system for home based stroke rehabilitation
Aisling Kelliher, Jinwoo Choi, Jia-Bin Huang, Kris Kitani, and Thanassis Rikakis
Proceedings of International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS), 2017
[Paper (PDF)] [Project page]

 

Visual Analysis and Synthesis with Physically Grounded Constraints
Jia-Bin Huang
Ph.D. Thesis, Department of Electrical and Computer Engineering
University of Illinois, Urbana-Champaign, August 2016
[Paper (PDF)] [Poster]

 

Temporally Coherent Completion of Dynamic Video
Jia-Bin Huang, Sing Bing Kang, Narendra Ahuja, and Johannes Kopf
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia), 2016
[Paper (PDF)] [Project page] [Code] [Mask] [Results]

 

Deep Joint Image Filter
Yijun Li, Jia-Bin Huang, Narendra Ahuja, and Ming-Hsuan Yang
Proceedings of European Conference on Computer Vision (ECCV), 2016
[Paper (PDF)] [Project page] [Code] [Supp] [Poster]

 

Tracking Persons-of-Interest via Adaptive Discriminative Features
Shun Zhang, Yihong Gong, Jia-Bin Huang, Jongwoo Lim, Jinjun Wang, Narendra Ahuja, and Ming-Hsuan Yang
Proceedings of European Conference on Computer Vision (ECCV), 2016
[Paper (PDF)] [Project page] [Code] [Supp] [Poster]

 

Unsupervised Visual Representation Learning by Graph-based Consistent Constraints
Dong Li, Wei-Chih Hung, Jia-Bin Huang, Shengjin Wang, Narendra Ahuja, and Ming-Hsuan Yang
Proceedings of European Conference on Computer Vision (ECCV), 2016
[Paper (PDF)] [Project page] [Code] [Supp] [Slides] [Poster]

 

Detecting Migrating Birds at Night
Jia-Bin Huang, Rich Caruana, Andrew Farnsworth, Steve Kelling, and Narendra Ahuja
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
[Paper (PDF)] [Project page] [Poster]

 

A Comparative Study for Single Image Blind Deblurring
Wei-Sheng Lai, Jia-Bin Huang, Zhe Hu, Narendra Ahuja, and Ming-Hsuan Yang
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 (Spotlight Oral)
[Paper (PDF)] [Project page] [Code] [Supp] [Slides] [Poster]

 

Weakly Supervised Object Localization with Progressive Domain Adaptation
Dong Li, Jia-Bin Huang, Yali Li, Shengjin Wang, and Ming-Hsuan Yang
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
[Paper (PDF)] [Project page] [Code] [Supp] [Poster]

 

Hierarchical Convolutional Features for Visual Tracking
Chao Ma, Jia-Bin Huang, Xiaokang Yang, and Ming-Hsuan Yang
Proceedings of IEEE International Conference on Computer Vision (ICCV), 2015
[Paper (PDF)] [Project page] [Code] [Supp] [Slides] [Poster]

 

Single Image Super-Resolution from Transformed Self-Exemplars
Jia-Bin Huang, Abhishek Singh, and Narendra Ahuja
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015 (Oral Presentation)
[Paper (PDF)] [Project page] [Code] [Supp] [Talk] [Slides] [Poster]

 

Image Completion using Planar Structure Guidance
Jia-Bin Huang, Sing Bing Kang, Narendra Ahuja, and Johannes Kopf
ACM Transactions on Graphics, Volume 33, Number 4 (SIGGRAPH), 2014 (Oral Presentation)
[Paper (PDF)] [Project page] [2014 Completion_Slides.pdf Slides] [Supp]

 

Towards Accurate and Robust Cross-Ratio based Gaze Trackers Through Learning From Simulation
Jia-Bin Huang, Qin Cai, Zicheng Liu, Narendra Ahuja, and Zhengyou Zhang
Proceedings of ACM Symposium on Eye Tracking Research & Applications (ETRA), 2014 (Oral Presentation)
[Paper (PDF)] [Project page] [Slides]
ETRA 2014 Best Paper Award [Patent]: Eye Gaze Tracking based upon Adaptive Homography Mapping

 

Transformation Guided Image Completion
Jia-Bin Huang, Johannes Kopf, Narendra Ahuja, and Sing Bing Kang
Proceedings of IEEE Conference on International Conference on Computational Photography (ICCP), 2013 (Oral Presentation)
[Paper (PDF)] [Project page] [Slides] [Supplementary material]

 

Saliency Detection via Divergence Analysis: A Unified Perspective
Jia-Bin Huang and Narendra Ahuja
Proceedings of International Conference on Pattern Recognition (ICPR), 2012 (Oral Presentation)
[Paper (PDF)] [Project page] [Slides]

ICPR 2012 Best Student Paper Award (Computer and Robotic Vision Track)

 

Exploiting Self-Similarities for Single Frame Super-Resolution
Chih-Yuan Yang, Jia-Bin Huang, and Ming-Hsuan Yang
Proceedings of Asian Conference on Computer Vision (ACCV), 2010
[Paper (PDF)] [Project page] [Poster]

 

Single Image Deblurring with Adaptive Dictionary Learning
Zhe Hu, Jia-Bin Huang, and Ming-Hsuan Yang
Proceedings of IEEE International Conference on Image Processing (ICIP), 2010.
[Paper (PDF)] [Project page] [Poster]

 

Fast Sparse Representation with Prototypes
Jia-Bin Huang and Ming-Hsuan Yang
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010.
[Paper (PDF)] [Project page] [Poster]

 

Estimating Human Pose from Occluded Images
Jia-Bin Huang and Ming-Hsuan Yang
Proceedings of Asian Conference on Computer Vision (ACCV), 2009 (Oral Presentation)
[Paper (PDF) ] [Project page] [Slides]

 

Moving Cast Shadow Detection Using Physics-based Features
Jia-Bin Huang and Chu-Song Chen
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009
[Paper (PDF)] [Project page] [Poster]

 

A Physical Approach to Moving Cast Shadow Detection
Jia-Bin Huang and Chu-Song Chen
Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, (ICASSP), 2009
[Paper (PDF)] [Project page]

 

Image Recolorization For The Colorblind
Jia-Bin Huang, Chu-Song Chen Tzu-Cheng Jen, and Sheng-Jyh Wang
Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, (ICASSP), 2009
[Paper (PDF)] [Project page]

 

Learning Moving Cast Shadows for Foreground Detection
Jia-Bin Huang and Chu-Song Chen
Eighth International Workshop on Visual Surveillance (VS), ECCV Workshop 2008 (Oral Presentation)
[Paper (PDF)] [Project page]

 

Enhancing Color Representation for the Color Vision Impaired
Jia-Bin Huang, Sih-Ying Wu and Chu-Song Chen
Workshop on Computer Vision Applications for the Visually Impaired (CVAVI), ECCV Workshop 2008 (Oral Presentation)
[Paper (PDF)] [Project page]

CVGIP 2008 Best Paper Honorable Mention

 

Information Preserving Color Transformation for Protanopia and Deuteranopia
Jia-Bin Huang, Yu-Cheng-Tseng, Se-In Wu, and Sheng-Jyh Wang
IEEE Signal Processing Letters, Vol. No.10, October 2007
[Paper (PDF)] [Project page]

CVGIP 2006 Best Paper Honorable Mention

Open Office Hour

I set aside some time some weeks to meet with anyone (preferrably students from underrepresented groups). Free free to sign up below if you would like to chat with me on any topics.

Recent talks

12/08/2022 GRAIL Vision Seminar at University of Washington
12/05/2022 Faculty Job Workshop at University of Maryland College Park [Slides]
11/21/2022 Computer Science and Engineering AI Seminar at Ohio State University
11/18/2022 Invited guest lecture in CS197 at Harvard University [Slides]
11/18/2022 CS Department Seminar at Virginia Tech
10/14/2021 Invited talk at 2021 華仁全球講座 (Host: Jenq-Neng Hwang)
08/26/2021 Invited talk at Graphics And Mixed Environment Seminar (Host: Jun-Yan Zhu)
07/20/2021 Invited talk at School of Computer Science, Tel Aviv University (Host: Daniel Cohen-Or)
07/13/2021 Invited talk at VGG seminar, University of Oxford
07/07/2021 Invited talk at IMAGINE lab, Ecole des Ponts ParisTech
05/10/2021 Invited talk at National Yang Ming Chiao Tung University
04/23/2021 Invited talk at UT Austin (Host: Zhangyang Wang)
04/20/2021 School of Interactive Computing Seminar at Georgia Tech (Host: Frank Dellaert)
04/08/2021 CS Colloquium at Cornell University (Host: Noah Snavely)
04/05/2021 ECE Seminar at the University of Michigan
03/29/2021 CS Colloquium at University of Maryland (Host: Abhinav Shrivastava)
03/22/2021 CS Colloquium at University of North Carolina Chapel Hill (Host: Mohit Bansal)
02/26/2021 EECS Department Seminar at UC Merced (Host: Ming-Hsuan Yang)
02/05/2021 3M Non-Tenured Faculty Award Symposium
02/02/2021 Visual Information Laboratory Seminar, University of Bristol (Host: Dima Damen)
01/26/2021 Computer Vision Seminar, University of Illinois, Urbana-Champaign
01/20/2021 3D Representations Reading Group at MIT [Video] [Slides]

Highlights and News

09 / 2022 Thanks Adobe, Meta, Google for the gift donation.
06 / 2021 Thanks Virginia’s Commonwealth Cyber Initiative for the grants on Detecting Disinformation and Misinformation (with Ruoxi Jia Adrienne Ivory)
04 / 2021 Thanks Center for Human-Computer Interaction for the Planning Grants for Large-scale Research Efforts(with Douglas Bowman, Joe Gabbard,Nazila Roofigari-Esfahan, and Hoda Eldardiry)
04 / 2021 Congrats to Esther and Meng-Li for getting into top PhD programs!Esther will join CS@Stanford University. Meng-Li will join CSE @ University of Washington.
08 / 2020 Thanks Facebook and Adobe for the gift donation.
08 / 2020 Thank NSF for the Smart and Connected Health (SCH) grant (1.1M for four years).
03 / 2020 Thank 3M for supporting our work with the 3M Non-Tenure Faculty Award.
02 / 2020 Thanks 4-VA for the supporting us with a collaborative research grant (with Vicente Ordonez at University of Virginia).
09 / 2019 Thanks NSF for supporting us with a medium Cyber-Physical Systems (CPS) grant (with Ryan K. Williams, Haibo Zeng, Changhee Jung).
09 / 2019 Thanks Rehabilitation Engineering Research Centers (RERC) for supporting us through the Rehabilitation Strategies, Techniques, and Interventions program (with Shirley Ryan Ability Lab, Thanassis Rikakis, Aisling Kelliher).
04 / 2019 Thanks SAMSUNG for continuing to support our research through the GRO award (with Alexander Schwing).
02 / 2019 Thanks Google for supporting our research with the Google Faculty Research Award.
04 / 2018 Thanks NSF for supporting our research with an CRII award.

Recent Community Services

Computer Vision

Computer Graphics

Artificial Intelligence / Machine Learning

Mentoring

Teaching

University of Maryland College Park

Virginia Tech