Kwan-Yee (Jun-Yi) Lin

I am currently a Research Scientist at Shanghai AI Laboratory. I have been a post-doc researcher at MMLab, The Chinese University of Hong Kong, working with Prof. Hongsheng Li and Prof. Xiaogang Wang. Previously, I was the Director of R&D at Intelligent Automotive Group of SenseTime Group Inc., working with Chen Qian. During my time at SenseTime, I led the development and research of 3D Perceiving R&D Centre, which served for several leading automakers (e.g., BMW, Honda and NIO) and had delivered 30+ mass-produced projects in the intelligent cabin industry. I received my PhD degree in the Department of Information Science, School of Mathematical Sciences at Peking University.
My research interests lie at the intersection of Computer Vision, Computer Graphics, and Machine Learning. I am particularly interested in 3d scene understanding, high-fidelity digital human, and 3D content creation.
** Joint programs of PhD, RA at NTU and CUHK are open! **
** Job positions are open for researchers and interns at Shanghai AI Lab! **
News
Sep, 2022 | We are starting OpenXDLab, a new large-scale open-source project for datasets of XR research! 🔥 |
---|---|
Jul, 2022 | 3 papers with 1 oral presentations got accepted by CVPR/ECCV 2022. |
Mar, 2021 | 2 papers with 1 oral presentations got accepted by CVPR 2021. |
Jul, 2020 | 2 papers got accepted by CVPR/ECCV in 2020. |
Jul, 2020 | We released MMDetection3D, OpenMMLab’s Next-Generation Platform for 3D Object Detection. |
Jul, 2019 | 3 papers with 2 oral presentations got accepted by CVPR/ICCV in 2019. |
Jul, 2018 | 2 papers got accepted by CVPR/BMVC in 2018. |
Selected Publications
- Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View SynthesisTechnical report, arXiv:2204.11798, 2022
- Simulating Fluids in Real-World Still ImagesTechnical report, arXiv:2204.11335, 2022
- StyleGAN-Human: A Data-Centric Odyssey of Human GenerationEuropean Conference on Computer Vision (ECCV), 2022
- Semantic Scene Completion via Integrating Instances and Scene in-the-LoopConference on Computer Vision and Pattern Recognition (CVPR), 2021
- 3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure PriorConference on Computer Vision and Pattern Recognition (CVPR), 2020
- Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose EstimationConference on Computer Vision and Pattern Recognition (CVPR), 2019 (Oral)
- Hallucinated-IQA: No-reference Image Quality Assessment via Adversarial LearningConference on Computer Vision and Pattern Recognition (CVPR), 2018