Wei-Sheng (Jason) Lai

Unsplashed background img 1


About Me

I am a senior software engineer at Google, working on mobile computational photography. I received my Ph.D. from the EECS department at University of California, Merced in 2019, under the advisement of Prof. Ming-Hsuan Yang. Before coming to UC Merced in 2015, I obtained my B.S. and M.S. degrees from the EE department at National Taiwan University in 2012 and 2014, respectively.

My research interests include Computer Vision, Computational Photography and Machine Learning. I am lucky to have opportunities to work with Jia-Bin Huang (Virginia Tech), YiChang Shih (Google), Chia-Kai Liang (Google), Deqing Sun (Nvidia Research), Jinwei Gu (Nvidia Research), Orazio Gallo (Nvidia Research), Jan Kautz (Nvidia Research), Ersin Yumer (Adobe Research), Oliver Wang (Adobe Research), Eli Shechtman (Adobe Research), Neel Joshi (Microsoft Research), Sing Bing Kang (Microsoft Research), Yen-Yu Lin (Academia Sinica), and Yung-Yu Chuang (National Taiwan University).

I have collaborated with the following interns so far: Kai-En Lin (2021), Xide Xia (2020), Zhenmei Shi (2020), Chen Gao (2020).

Publications

Face Deblurring using Dual Camera Fusion on Mobile Phones
ACM Transactions on Graphics (SIGGRAPH), 2022
paper
project website
Vision Transformer for NeRF-Based View Synthesis from a Single Input Image
arXiv, 2022
paper
project website
Correcting Face Distortion in Wide-Angle Videos
IEEE Transactions on Image Processing (TIP), 2021
paper
project website
Stylizing 3D Scene via Implicit Representation and HyperNetwork
Pei-Ze Chiang, Meng-Shiun Tsai, Hung-Yu Tseng, Wei-Sheng Lai, and Wei-Chen Chiu
IEEE Winter Conference on Applications of Computer Vision (WACV), 2022
paper
project website
Deep Online Fused Video Stabilization
IEEE Winter Conference on Applications of Computer Vision (WACV), 2022
paper
project website
Learning to See Through Obstructions with Layered Decomposition
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 2021
paper [CVPR'20] [TPAMI'21]
project website [CVPR'20] [TPAMI'21]
code [CVPR'20] [TPAMI'21]
Toward Real-World Super-Resolution via Adaptive Downsampling Models
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 2021
paper
supplementary material
Hybrid Neural Fusion for Full-frame Video Stabilization
IEEE International Conference on Computer Vision (ICCV), 2021
paper
project website
code
Portrait Neural Radiance Fields from a Single Image
arXiv, 2021
paper
project website
Dual-Stream Fusion Network for Spatiotemporal Video Super-Resolution
Min-Yuan Tseng, Yen-Chung Chen, Yi-Lun Lee, Wei-Sheng Lai, Yi-Hsuan Tsai and Wei-Chen Chiu
IEEE Winter Conference on Applications of Computer Vision (WACV), 2021
paper
Supplementary material
Real-time Localized Photorealistic Video Style Transfer
Xide Xia, Tianfan Xue, Wei-Sheng Lai, Zheng Sun, Abby Chang, Brian Kulis and Jiawen Chen
IEEE Winter Conference on Applications of Computer Vision (WACV), 2021
paper
Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
paper
project website
code
Dynamic Scene Deblurring by Depth Guided Model
Lerenhan Li, Jinshan Pan, Wei-Sheng Lai, Changxin Gao, Nong Sang and Ming-Hsuan Yang
IEEE Transactions on Image Processing (TIP), 2020
paper
Visual Question Answering on 360° Images
Winter Conference on Applications of Computer Vision (WACV), 2020
paper
project website
Deep Semantic Face Deblurring
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
International Journal of Computer Vision (IJCV), 2020
conference version
journal version
project website
Gated Fusion Network for Degraded Image Super Resolution
Xinyi Zhang, Hang Dong, Zhe Hu, Wei-Sheng Lai, Fei Wang, and Ming-Hsuan Yang
British Machine Vision Conference (BMVC), 2018 (Oral presentation)
International Journal of Computer Vision (IJCV), 2020
conference version
journal version
project website
Video Stitching for Linear Camera Arrays
British Machine Vision Conference (BMVC), 2019
paper
project website
Distortion-Free Wide-Angle Portraits on Camera Phones
ACM Transactions on Graphics (SIGGRAPH), 2019
paper
project website
Depth-Aware Video Frame Interpolation
Wenbo Bao, Wei-Sheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
paper
project website
code
MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Frame Interpolation and Enhancement
Wenbo Bao, Wei-Sheng Lai, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2019
paper
project website
Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2018
conference version
journal version
project website
code
Learning Blind Video Temporal Consistency
European Conference on Computer Vision (ECCV), 2018
paper
project website
Blind Image Deblurring via Deep Discriminative Priors
Lerenhan Li, Jinshan Pan, Wei-Sheng Lai, Changxin Gao, Nong Sang and Ming-Hsuan Yang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
International Journal of Computer Vision (IJCV), 2019
conference version
journal version
project website
Semi-Supervised Learning for Optical Flow with Generative Adversarial Networks
Neural Information Processing Systems (NIPS), 2017
paper
project website
Semantic-driven Generation of Hyperlapse from 360° Video
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2017
paper
project website
Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
paper
A Comparative Study for Single Image Blind Deblurring
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 (Spotlight presentation)
paper
project website
code
CVPR presentation
Blur Kernel Estimation Using Normalized Color-Line Priors
Wei-Sheng Lai, Jian-Jiun Ding, Yen-Yu Lin, and Yung-Yu Chuang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
paper
project website