# Physics-Aware Video Instance Removal Benchmark

arXiv: https://arxiv.org/abs/2604.05898 · HTML: https://mlsanity.com/paper/2604.05898/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 28 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 24 of 24)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [TokenFlow: Consistent Diffusion Features for Consistent Video Editing](https://mlsanity.com/paper/2307.10373/) (2023)
- [Video-P2P: Video Editing with Cross-attention Control](https://mlsanity.com/paper/2303.04761/) (2023)
- [YouTube-VOS: Sequence-to-Sequence Video Object Segmentation](https://mlsanity.com/paper/1809.00461/) (2018)
- [ProPainter: Improving Propagation and Transformer for Video Inpainting](https://mlsanity.com/paper/2309.03897/) (2023)
- [Towards An End-to-End Framework for Flow-Guided Video Inpainting](https://mlsanity.com/paper/2204.02663/) (2022)
- [FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting](https://mlsanity.com/paper/2109.02974/) (2021)
- [UniVideo: Unified Understanding, Generation, and Editing for Videos](https://mlsanity.com/paper/2510.08377/) (2025)
- [DiffuEraser: A Diffusion Model for Video Inpainting](https://mlsanity.com/paper/2501.10018/) (2025)
- [CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility](https://mlsanity.com/paper/2403.12035/) (2024)
- [AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling](https://mlsanity.com/paper/2111.00772/) (2021)
- [ROSE: Remove Objects with Side Effects in Videos](https://mlsanity.com/paper/2508.18633/) (2025)
- [IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment](https://mlsanity.com/paper/2510.11647/) (2025)
- [PISCO: Precise Video Instance Insertion with Sparse Control](https://mlsanity.com/paper/2602.08277/) (2026)
- [VOID: Video Object and Interaction Deletion](https://mlsanity.com/paper/2604.02296/) (2026)
- [The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics](https://mlsanity.com/paper/2603.14375/) (2026)

## Built on by (most cited first, 3 of 3)

- [VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects](https://mlsanity.com/paper/2604.16272/) (2026)
- [VideoPhysEdit: Physical Counterfactual Video Editing via Rigid-Body Physical Scene Reconstruction](https://mlsanity.com/paper/2609.35134/) (2026)
- [ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing](https://mlsanity.com/paper/2609.40356/) (2026)

## Abstract (arXiv)

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.