3 papers
cs.CV2025
PostCam: Camera-Controllable Novel-View Video Generation with Query-Shared Cross-Attention
Yipeng Chen, Zhichao Ye, Zhenzhou Fang +6
We propose PostCam, a streamlined framework for novel-view video generation that achieves superior detail preservation and precise camera trajectory editing in dynamic scenes. Curr…
cs.CV2024
StarVid: Enhancing Semantic Alignment in Video Diffusion Models via Spatial and SynTactic Guided Attention Refocusing
Yuanhang Li, Qi Mao, Lan Chen +5
Recent advances in text-to-video (T2V) generation with diffusion models have garnered significant attention. However, they typically perform well in scenes with a single object and…
cs.CV2023
MAG-Edit: Localized Image Editing in Complex Scenarios via Mask-Based Attention-Adjusted Guidance
Qi Mao, Lan Chen, Yuchao Gu +2
Recent diffusion-based image editing approaches have exhibited impressive editing capabilities in images with simple compositions. However, localized editing in complex scenarios h…