|
Yixuan Ren I am a Ph.D. student in the Department of Computer Science at the University of Maryland, College Park, advised by Professor Abhinav Shrivastava. My research focuses on image/video sythensis and editing with deep generative models. I'm also interested in implicit neural representations especially for generative tasks. |
|
Publications |
|
|
Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models
Yixuan Ren, Yang Zhou, Jimei Yang, Jing Shi, Difan Liu, Feng Liu, Mingi Kwon, Abhinav Shrivastava arXiv, 2024 project page / paper / arxiv / code Customize pre-trained video diffusion models from a single reference video and adapt its motion to new subjects and scenes with motion diversity. |
|
Content-Adapt Image Color Editing With Auxiliary Color Restoration Tasks
Yixuan Ren, Jing Shi, Zhifei Zhang, Yifei Fan, Zhe Lin, Bo He, Abhinav Shrivastava WACV, 2024 paper / code Edit image color with styles adaptive to its content. |
|
Towards Scalable Neural Representation for Diverse Videos
Bo He, Xitong Yang, Hanyu Wang, Zuxuan Wu, Hao Chen, Shuaiyi Huang, Yixuan Ren, Ser-Nam Lim, Abhinav Shrivastava CVPR, 2023 project page / arxiv / code Video INR to encode large-scale and diverse video data. |
|
NeRV: Neural Representations for Videos
Hao Chen, Bo He, Hanyu Wang, Yixuan Ren, Ser-Nam Lim, Abhinav Shrivastava NeurIPS, 2021 project page / arxiv / code A frame-wise neural representation for videos, achieveing good compression performance and fast decoding speed. |
|
StEP: Style-based Encoder Pre-training for Multi-modal Image Synthesis
Moustafa Meshry, Yixuan Ren, Larry S. Davis, Abhinav Shrivastava CVPR, 2021 project page / paper / arxiv / code A staged MMI2I method via style encoder pre-training for simplifed losses and stablized training. |
Experiences
|
Services
|
|
Thank Dr. Jon Barron for sharing the awesome source code of his personal page. |