# VOID: Video Object and Interaction Deletion

arXiv: https://arxiv.org/abs/2604.02296 · HTML: https://mlsanity.com/paper/2604.02296/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 45 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 30 of 39)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [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)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark](https://mlsanity.com/paper/1809.03327/) (2018)
- [Kubric: A scalable dataset generator](https://mlsanity.com/paper/2203.03570/) (2022)
- [MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark](https://mlsanity.com/paper/2402.04788/) (2024)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [ProPainter: Improving Propagation and Transformer for Video Inpainting](https://mlsanity.com/paper/2309.03897/) (2023)
- [Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control](https://mlsanity.com/paper/2501.03847/) (2025)
- [Do generative video models understand physical principles?](https://mlsanity.com/paper/2501.09038/) (2025)
- [PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding](https://mlsanity.com/paper/2501.16411/) (2025)
- [LLaVA-Critic: Learning to Evaluate Multimodal Models](https://mlsanity.com/paper/2410.02712/) (2024)
- [Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise](https://mlsanity.com/paper/2501.08331/) (2025)
- [VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models](https://mlsanity.com/paper/2502.02492/) (2025)
- [AVID: Any-Length Video Inpainting with Diffusion Model](https://mlsanity.com/paper/2312.03816/) (2023)
- [DiffuEraser: A Diffusion Model for Video Inpainting](https://mlsanity.com/paper/2501.10018/) (2025)
- [Omnimatte: Associating Objects and Their Effects in Video](https://mlsanity.com/paper/2105.06993/) (2021)
- [MiniMax-Remover: Taming Bad Noise Helps Video Object Removal](https://mlsanity.com/paper/2505.24873/) (2025)
- [Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation](https://mlsanity.com/paper/2412.06016/) (2024)
- [VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation](https://mlsanity.com/paper/2503.14350/) (2025)
- [Generative Omnimatte: Learning to Decompose Video into Layers](https://mlsanity.com/paper/2411.16683/) (2024)
- [ROSE: Remove Objects with Side Effects in Videos](https://mlsanity.com/paper/2508.18633/) (2025)
- [HUMOTO: A 4D Dataset of Mocap Human Object Interactions](https://mlsanity.com/paper/2504.10414/) (2025)
- [TRAVL: A Recipe for Making Video-Language Models Better Judges of Physics Implausibility](https://mlsanity.com/paper/2510.07550/) (2025)

## Built on by (most cited first, 9 of 9)

- [VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects](https://mlsanity.com/paper/2604.16272/) (2026)
- [Physics-Aware Video Instance Removal Benchmark](https://mlsanity.com/paper/2604.05898/) (2026)
- [EditStream: A Unified Autoregressive Framework for Interactive Video Generation and Editing](https://mlsanity.com/paper/2608.21424/) (2026)
- [Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation](https://mlsanity.com/paper/2606.20118/) (2026)
- [DexAgent: An Agentic Human2Sim2Robot Framework for Dexterous Manipulation with Self-Evolving Tool Library](https://mlsanity.com/paper/2609.35318/) (2026)
- [AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance](https://mlsanity.com/paper/2606.01362/) (2026)
- [EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal](https://mlsanity.com/paper/2608.05565/) (2026)
- [VOR-Bench: A Human Perception-Driven Benchmark for Video Object Removal](https://mlsanity.com/paper/2609.16878/) (2026)
- [Reimagine Video Dynamics](https://mlsanity.com/paper/2609.36496/) (2026)

## Abstract (arXiv)

Existing video object removal methods excel at inpainting content "behind" the object and correcting appearance-level artifacts such as shadows and reflections. However, when the removed object has more significant interactions, such as collisions with other objects, current models fail to correct them and produce implausible results. We present VOID, a video object removal framework designed to perform physically-plausible inpainting in these complex scenarios. To train the model, we generate a new paired dataset of counterfactual object removals using Kubric and HUMOTO, where removing an object requires altering downstream physical interactions. During inference, a vision-language model identifies regions of the scene affected by the removed object. These regions are then used to guide a video diffusion model that generates physically consistent counterfactual outcomes. Experiments on both synthetic and real data show that our approach better preserves consistent scene dynamics after object removal compared to prior video object removal methods. We hope this framework sheds light on how to make video editing models better simulators of the world through high-level causal reasoning.