Physics-Aware Video Instance Removal Benchmark

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

Submission Type: Full Papers (up to 8 pages)

Keywords: Video Instance Removal, Benchmark and Evaluation, Physics-Aware Video Editing, World Model, AI-assisted Film-making

TL;DR: The PVIR benchmark evaluates video editing models on their ability to seamlessly erase objects while preserving complex physical side effects like shadows and reflections.

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.

Submission Number: 5