Beyond Rigid: Benchmarking Non-Rigid Video Editing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qu, Bingzheng, Bai, Xuefeng, Chen, Kehai, Zhang, Min
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910280650326016
author Qu, Bingzheng
Bai, Xuefeng
Chen, Kehai
Zhang, Min
author_facet Qu, Bingzheng
Bai, Xuefeng
Chen, Kehai
Zhang, Min
contents As video generation models are increasingly expected to manipulate physical dynamics, there is a growing need to move evaluation beyond appearance fidelity and semantic alignment. Non-rigid video editing offers a uniquely revealing testbed, where distinct materials impose distinct physical constraints. In this paper, we introduce NRVBench, a diagnostic benchmark for non-rigid video editing, where the task is to modify deformable motion while preserving irrelevant regions and maintaining material-specific plausibility. NRVBench contains 180 curated videos across six physics-grounded categories, 2,340 fine-grained editing instructions, 360 multiple-choice questions, and pixel-accurate masks. We further propose NRVE-Acc, a structured VLM-based protocol that decomposes editing success into instruction following, material-aware deformation plausibility, and temporal coherence with motion cues. Experiments on representative inference-time video editing methods reveal a clear mismatch between conventional metrics and physics-aware perceptual editing success: methods that preserve appearance or achieve strong global alignment may still fail under non-rigid dynamics. We additionally introduce VM-Edit, a simple region-conditioned editing baseline that frees the foreground while locking the background, exposing the stability--plasticity trade-off.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18340
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Rigid: Benchmarking Non-Rigid Video Editing
Qu, Bingzheng
Bai, Xuefeng
Chen, Kehai
Zhang, Min
Computer Vision and Pattern Recognition
As video generation models are increasingly expected to manipulate physical dynamics, there is a growing need to move evaluation beyond appearance fidelity and semantic alignment. Non-rigid video editing offers a uniquely revealing testbed, where distinct materials impose distinct physical constraints. In this paper, we introduce NRVBench, a diagnostic benchmark for non-rigid video editing, where the task is to modify deformable motion while preserving irrelevant regions and maintaining material-specific plausibility. NRVBench contains 180 curated videos across six physics-grounded categories, 2,340 fine-grained editing instructions, 360 multiple-choice questions, and pixel-accurate masks. We further propose NRVE-Acc, a structured VLM-based protocol that decomposes editing success into instruction following, material-aware deformation plausibility, and temporal coherence with motion cues. Experiments on representative inference-time video editing methods reveal a clear mismatch between conventional metrics and physics-aware perceptual editing success: methods that preserve appearance or achieve strong global alignment may still fail under non-rigid dynamics. We additionally introduce VM-Edit, a simple region-conditioned editing baseline that frees the foreground while locking the background, exposing the stability--plasticity trade-off.
title Beyond Rigid: Benchmarking Non-Rigid Video Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.18340