Tao Zhang, XingYe Tian, Yu Wu, ShunPing Ji, Xuebo Wang, Yuan Zhang, Pengfei Wan
- DVIS is a universal video segmentation framework that supports VIS, VPS and VSS.
- DVIS can run in both online and offline modes.
- DVIS achieved SOTA performance on YTVIS, OVIS, VIPSeg and VSPW datasets.
- DVIS can complete training and inference on GPUs with only 11G memory.
See Installation Instructions.
See Preparing Datasets for DVIS.
See Getting Started with DVIS.
Trained models are available for download in the DVIS Model Zoo.
This repo is largely based on Mask2Former, MinVIS and VITA. Thanks for their excellent works.