65 citations · 101 across the 2 of their papers we have counts for
3 papers
cs.CV2025
MTV-Inpaint: Multi-Task Long Video Inpainting
Shiyuan Yang, Zheng Gu, Liang Hou +4
Video inpainting involves modifying local regions within a video, ensuring spatial and temporal consistency. Most existing methods focus primarily on scene completion (i.e., fillin…
cs.CV2024★ 36 cited
Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion
Shiyuan Yang, Liang Hou, Haibin Huang +5
Recent text-to-video diffusion models have achieved impressive progress. In practice, users often desire the ability to control object motion and camera movement independently for…
cs.CV2023★ 65 cited
Uni-paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Model
Shiyuan Yang, Xiaodong Chen, Jing Liao
Recently, text-to-image denoising diffusion probabilistic models (DDPMs) have demonstrated impressive image generation capabilities and have also been successfully applied to image…