Lune

CVPR2025

VidSeg: Training-free Video Semantic Segmentation based on Diffusion Models

Qian Wang, Abdelrahman Eldesokey, Mohit Mendiratta, Fangneng Zhan, Adam Kortylewski, Christian Theobalt, Peter Wonka

DOI出版方

摘要

Figure 1. We propose the first training-free diffusion-based approach for Video Semantic Segmentation (VSS). Our approach produces temporally consistent predictions compared to the diffusion-based image segmentation method EmerDiff [15].