# PROVE: A Perceptual RemOVal cohErence Benchmark for Visual Media

arXiv: https://arxiv.org/abs/2605.14534 · HTML: https://mlsanity.com/paper/2605.14534/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 43 references that are in the map.
- First posted on arXiv 14 May 2026.

## Builds on (most cited first, 9 of 9)

- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [DiffuEraser: A Diffusion Model for Video Inpainting](https://mlsanity.com/paper/2501.10018/) (2025)
- [MiniMax-Remover: Taming Bad Noise Helps Video Object Removal](https://mlsanity.com/paper/2505.24873/) (2025)
- [ROSE: Remove Objects with Side Effects in Videos](https://mlsanity.com/paper/2508.18633/) (2025)
- [OmniEraser: Remove Objects and Their Effects in Images with Paired Video-Frame Data](https://mlsanity.com/paper/2501.07397/) (2025)
- [Attacking Perceptual Similarity Metrics](https://mlsanity.com/paper/2305.08840/) (2023)
- [Object-WIPER : Training-Free Object and Associated Effect Removal in Videos](https://mlsanity.com/paper/2601.06391/) (2026)

## Built on by (most cited first, 2 of 2)

- [TripleFlow: Training-Free Video Object Removal by Bridging Residual Editing and Native Generation](https://mlsanity.com/paper/2609.39157/) (2026)
- [MFVSR: A Multi-Style and Fine-Grained Benchmark for Video Subtitle Removal](https://mlsanity.com/paper/2610.18461/) (2026)

## Abstract (arXiv)

Evaluating object removal in images and videos remains challenging because the task is inherently one-to-many, yet existing metrics frequently disagree with human perception. Full-reference metrics reward copy-paste behaviors over genuine erasure; no-reference metrics suffer from systematic biases such as favoring blurry results; and global temporal metrics are insensitive to localized artifacts within edited regions. To address these limitations, we propose RC (Removal Coherence), a pair of perception-aligned metrics: RC-S, which measures spatial coherence via sliding-window feature comparison between masked and background regions, and RC-T, which measures temporal consistency via distribution tracking within shared restored regions across adjacent frames. To validate RC and support community benchmarking, we further introduce PROVE-Bench, a two-tier real-world benchmark comprising PROVE-M, an 80-video paired dataset with motion augmentation, and PROVE-H, a 100-video challenging subset without ground truth. Together, RC metrics and PROVE-Bench form the PROVE (Perceptual RemOVal cohErence) evaluation framework for visual media. Experiments across diverse image and video benchmarks demonstrate that RC achieves substantially stronger alignment with human judgments than existing evaluation protocols. Project page: https://xiaomi-research.github.io/prove/.