AI Paper Atlas

Research map / Video / Video generation

VOID: Video Object and Interaction Deletion

Saman Motamed, William Harvey, Benjamin Klein, Luc Van Gool, Zhuoning Yuan, Ta-Ying Cheng

ECCV 2026 · Video › Video generation · approach: Diffusion-based video editing · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
counterfactual physics-aware removal (VOID) instead of Runway text editingvideo object removal · Real-world videos, human preferencewin %: 18.4 -> 64.8Improved
VOID versus best baselines on VLM judgesvideo object removal · Real-world videos, three VLM judgestotal score: 25.05 -> 26.13 (Gemini); 20.21 -> 23.16 (GPT-5.2)Improved
VOID versus baselines on synthetic counterfactual benchmarkvideo object removal · Synthetic benchmarkFVD: 437.88 -> 260.31Improved
VOID versus ProPainter on LPIPSvideo object removal · Synthetic benchmarkLPIPS: 0.0981 -> 0.1156Hurt
mix Kubric and HUMOTO data instead of a single dataset (size fixed at 1200) (ablation)VOID training · Real-world videos, Gemini judgetotal score: 20.36 / 20.12 -> 21.93Improved
use VLM-guided quadmask instead of simple trimask (ablation)VOID · Real-world videos, Gemini judgetotal score: 23.39 -> 26.12Improved
use Gemini 3 Pro as mask VLM rather than Qwen3-32B or GPT 5.2 (ablation)VOID inference · Real-world videos, Gemini judgetotal score: 23.91 / 24.34 -> 26.12Improved
add flow-warped noise second pass (ablation)VOID · 10 flagged real-world videostotal score: 23.5 -> 26.0Improved
second pass on preservation score (ablation)VOID · 10 flagged real-world videosPreservation (0-5): 4.90 -> 4.80Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy