VIRST: Video-Instructed Reasoning Assistant for SpatioTemporal Segmentation

CVPR 2026

Official implementation of VIRST, a video-instructed reasoning framework for spatiotemporal segmentation.

TODO

• release model code
• release checkpoint
• release data code
• release utility scripts
• release training scripts
• eval script
• demo script

Overview

This repository contains the core training and evaluation code for VIRST, including:

• model definition in model/
• training entrypoints in train.py and train_stage3.py
• RVOS evaluation in eval.py
• dataset handling in data/
• utility code in utils/

Checkpoint

Pretrained checkpoint: Google Drive

Notes

• The project page will be updated as the release is polished further.

Acknowledgements

This project builds upon prior work, including VISA, LISA, VideoChat-Flash, and SAM2.

We thank the authors for releasing their code and models.