|
Yixuan Ren I am a Ph.D. student in the Department of Computer Science at the University of Maryland, College Park, advised by Prof. Abhinav Shrivastava. Prior to that, I received my B.E. degree from Tsinghua University. My research focuses on image/video synthesis and editing with deep generative models. I'm also interested in video implicit neural representations especially for generative tasks. Email / Google Scholar / LinkedIn / Bluesky |
|
Publications |
|
Diffuse Implicit Neural Representation for Video Synthesis
Yixuan Ren, Hanyu Wang, Hao Chen, Bo He, Abhinav Shrivastava Under Review, 2024 project page / paper Generate convolution weights via a diffusion model, which serve as the parameters of an implicit neural representation and self-decode to a synthesized video. |
|
Video Diffusion Models Encode Motions in Early Timesteps
Vatsal Baherwani, Yixuan Ren, Abhinav Shrivastava Under Review, 2024 project page (coming soon) We demonstrate that temporal signals are captured in the early denoising timesteps, and leverage this property toward more efficient one-shot video motion customization. |
|
LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior
Hanyu Wang, Saksham Suri, Yixuan Ren, Hao Chen, Abhinav Shrivastava Under Review, 2024 project page / arxiv / code A holistic video tokenizer that integrates a light weight autoregressive (AR) transformer to align the latent space with AR generative models. |
|
|
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 ECCV, 2024 project page / paper / arxiv / code (coming soon) Customize pre-trained video diffusion models from a single reference video and adapt its motion to new subjects and scenes with motion diversity. |
|
Content-Adaptive 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 / supplementary / code Edit the color tone of an image with the editing 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 A video implicit neural representation that encodes large-scale and diverse videos faithfully and efficiently. |
|
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 implicit neural representation for videos, of high 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 two-stage MMI2I method via style encoder pre-training for simplifed losses and stablized training. |
Experiences
|
Adobe Research, 2023
ByteDance, 2021
Services
†Outstanding Reviewer |
|
Thank Jon Barron for sharing the source code of his homepage. |