# VideoSAM: Open-World Video Segmentation

Source: [VideoSAM: Open-World Video Segmentation](<https://www.sota2.com/research/paper/68fa75361e209131cea66724>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:41:00.536Z

Authors: Pinxue Guo, Zixu Zhao, Jianxiong Gao, Chongruo Wu, Tong He, Zheng Zhang, Tianjun Xiao, Wenqiang Zhang

Published: 2024-10-11T12:56:32.000Z

## Abstract

Video segmentation is essential for advancing robotics and autonomous driving, particularly in open-world settings where continuous perception and object association across video frames are critical. While the Segment Anything Model (SAM) has excelled in static image segmentation, extending its capabilities to video segmentation poses significant challenges. We tackle two major hurdles: a) SAM's embedding limitations in associating objects across frames, and b) granularity inconsistencies in object segmentation. To this end, we introduce VideoSAM, an end-to-end framework designed to address these challenges by improving object tracking and segmentation consistency in dynamic environments. VideoSAM integrates an agglomerated backbone, RADIO, enabling object association through similarity metrics and introduces Cycle-ack-Pairs Propagation with a memory mechanism for stable object tracking. Additionally, we incorporate an autoregressive object-token mechanism within the SAM decoder to maintain consistent granularity across frames. Our method is extensively evaluated on the UVO and BURST benchmarks, and robotic videos from RoboTAP, demonstrating its effectiveness and robustness in real-world scenarios. All codes will be available.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2410.08781>)

[PDF](<https://arxiv.org/pdf/2410.08781.pdf>)
