Robust Promptable Video Object Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Sohyun, Gwon, Yeho, Hoyer, Lukas, Schindler, Konrad, Sakaridis, Christos, Kwak, Suha
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913116887973888
author Lee, Sohyun
Gwon, Yeho
Hoyer, Lukas
Schindler, Konrad
Sakaridis, Christos
Kwak, Suha
author_facet Lee, Sohyun
Gwon, Yeho
Hoyer, Lukas
Schindler, Konrad
Sakaridis, Christos
Kwak, Suha
contents The performance of promptable video object segmentation (PVOS) models substantially degrades under input corruptions, which prevents PVOS deployment in safety-critical domains. This paper offers the first comprehensive study on robust PVOS (RobustPVOS). We first construct a new, comprehensive benchmark with two real-world evaluation datasets of 351 video clips and more than 2,500 object masks under real-world adverse conditions. At the same time, we generate synthetic training data by applying diverse and temporally varying corruptions to existing VOS datasets. Moreover, we present a new RobustPVOS method, dubbed Memory-object-conditioned Gated-rank Adaptation (MoGA). The key to successfully performing RobustPVOS is two-fold: effectively handling object-specific degradation and ensuring temporal consistency in predictions. MoGA leverages object-specific representations maintained in memory across frames to condition the robustification process, which allows the model to handle each tracked object differently in a temporally consistent way. Extensive experiments on our benchmark validate MoGA's efficacy, showing consistent and significant improvements across diverse corruption types on both synthetic and real-world datasets, establishing a strong baseline for future RobustPVOS research. Our benchmark is publicly available at https://sohyun-l.github.io/RobustPVOS_project_page/.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12006
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Robust Promptable Video Object Segmentation
Lee, Sohyun
Gwon, Yeho
Hoyer, Lukas
Schindler, Konrad
Sakaridis, Christos
Kwak, Suha
Computer Vision and Pattern Recognition
The performance of promptable video object segmentation (PVOS) models substantially degrades under input corruptions, which prevents PVOS deployment in safety-critical domains. This paper offers the first comprehensive study on robust PVOS (RobustPVOS). We first construct a new, comprehensive benchmark with two real-world evaluation datasets of 351 video clips and more than 2,500 object masks under real-world adverse conditions. At the same time, we generate synthetic training data by applying diverse and temporally varying corruptions to existing VOS datasets. Moreover, we present a new RobustPVOS method, dubbed Memory-object-conditioned Gated-rank Adaptation (MoGA). The key to successfully performing RobustPVOS is two-fold: effectively handling object-specific degradation and ensuring temporal consistency in predictions. MoGA leverages object-specific representations maintained in memory across frames to condition the robustification process, which allows the model to handle each tracked object differently in a temporally consistent way. Extensive experiments on our benchmark validate MoGA's efficacy, showing consistent and significant improvements across diverse corruption types on both synthetic and real-world datasets, establishing a strong baseline for future RobustPVOS research. Our benchmark is publicly available at https://sohyun-l.github.io/RobustPVOS_project_page/.
title Robust Promptable Video Object Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.12006