← Back to archive day

Physics-Aware Video Instance Removal Benchmark

Zirui Li, Xinghao Chen, Lingyu Jiang, Dengzhe Hou, Fangzhou Lin, Kazunori Yamada, Xiangbo Gao, Zhengzhong Tu

35

Recommendation Score

breakthrough🔴 AdvancedComputer VisionVideo GenerationBenchmarkBest for researchers

Research context

Primary field

Computer Vision

Image, video, and 3D perception plus visual generation.

Topics

Video Generation

Paper type

Benchmark

Best for

Best for researchers

arXiv categories

cs.CVcs.CV

Why It Matters

PVIR introduces the first physics-aware benchmark for video object removal, forcing models to preserve physical consistency like shadows and reflections—critical for realistic video editing in production systems.

Abstract

Video Instance Removal (VIR) requires removing target objects while maintaining background integrity and physical consistency, such as specular reflections and illumination interactions. Despite advancements in text-guided editing, current benchmarks primarily assess visual plausibility, often overlooking the physical causalities, such as lingering shadows, triggered by object removal. We introduce the Physics-Aware Video Instance Removal (PVIR) benchmark, featuring 95 high-quality videos annotated with instance-accurate masks and removal prompts. PVIR is partitioned into Simple and Hard subsets, the latter explicitly targeting complex physical interactions. We evaluate four representative methods, PISCO-Removal, UniVideo, DiffuEraser, and CoCoCo, using a decoupled human evaluation protocol across three dimensions to isolate semantic, visual, and spatial failures: instruction following, rendering quality, and edit exclusivity. Our results show that PISCO-Removal and UniVideo achieve state-of-the-art performance, while DiffuEraser frequently introduces blurring artifacts and CoCoCo struggles significantly with instruction following. The persistent performance drop on the Hard subset highlights the ongoing challenge of recovering complex physical side effects.

Published April 7, 2026
© 2026 A2A.pub — AI to Action. From papers to practice, daily.
Summaries are AI-assistedPrivacyTerms