Related papers: VOID: Video Object and Interaction Deletion

VOID: Video Object and Interaction Deletion

URL: http://arxiv.org/abs/2604.02296v1
Date: Thu, 02 Apr 2026 17:36:53 GMT
Title: VOID: Video Object and Interaction Deletion
Abstract summary: Existing video object removal methods excel at inpainting content "behind" the object and correcting appearance-level artifacts such as shadows and reflections.<n>We present VOID, a video object removal framework designed to perform physically-plausible inpainting in complex scenarios.
Score: 50.155301620235285
License: http://creativecommons.org/licenses/by/4.0/
Abstract: 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.

Related papers

BeyondMasks: Evaluating Causal and Physical Consistency in Video Object Removal [27.338971504674983]
We introduce BeyondMasks, a paired benchmark for causally consistent video object removal.<n>The dataset spans diverse photometric, geometric, volumetric, and dynamic interactions.<n>We propose CORE, a structured vision language model based evaluation protocol.
arXiv Detail & Related papers (2026-08-20T14:37:40Z)
From Understanding to Erasing: Towards Complete and Stable Video Object Removal [8.035439287403983]
Video object removal aims to eliminate target objects from videos while plausibly completing missing regions and preservingtemporal consistency.<n>It remains challenging to remove object-induced side effects without compromising overall coherence.<n>This paper introduces understanding into erasing from two complementary perspectives.
arXiv Detail & Related papers (2026-04-02T06:50:39Z)
EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing [50.43992550991499]
Video object removal aims to eliminate dynamic target objects and their visual effects, such as deformation, shadows, and reflections, while restoring seamless backgrounds.<n>Recent diffusion-based video inpainting and object removal methods can remove the objects but often struggle to erase these effects and to synthesize coherent backgrounds.<n>We introduce VOR (Video Object Removal), a large-scale dataset that provides diverse paired videos.<n>We propose EffectErase, an effect-aware video object removal method that treats video object insertion as the inverse auxiliary task within a reciprocal learning scheme.
arXiv Detail & Related papers (2026-03-19T17:59:22Z)
ROSE: Remove Objects with Side Effects in Videos [47.196851721000655]
ROSE is a framework that studies the object's effects on environment, which can be categorized into five common cases: shadows, reflections, light, translucency and mirror.<n>To localize all object-correlated areas, the entire video is fed into the model for reference-based erasing.<n>Additional supervision is introduced to explicitly predict the areas affected by side effects, which can be revealed through the differential mask between the paired videos.
arXiv Detail & Related papers (2025-08-26T03:18:31Z)
ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion [34.29147907526832]
Diffusion models have revolutionized image editing but often generate images that violate physical laws. We propose a practical solution centered on a qcounterfactual dataset. By fine-tuning a diffusion model on this dataset, we are able to not only remove objects but also their effects on the scene.
arXiv Detail & Related papers (2024-03-27T17:59:52Z)
Discovering Objects that Can Move [55.743225595012966]
We study the problem of object discovery -- separating objects from the background without manual labels. Existing approaches utilize appearance cues, such as color, texture, and location, to group pixels into object-like regions. We choose to focus on dynamic objects -- entities that can move independently in the world.
arXiv Detail & Related papers (2022-03-18T21:13:56Z)
Occlusion-Aware Video Object Inpainting [72.38919601150175]
This paper presents occlusion-aware video object inpainting, which recovers both the complete shape and appearance for occluded objects in videos. Our technical contribution VOIN jointly performs video object shape completion and occluded texture generation. For more realistic results, VOIN is optimized using both T-PatchGAN and a newoc-temporal YouTube attention-based multi-class discriminator.
arXiv Detail & Related papers (2021-08-15T15:46:57Z)
RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces [77.07767833443256]
We present RELATE, a model that learns to generate physically plausible scenes and videos of multiple interacting objects. In contrast to state-of-the-art methods in object-centric generative modeling, RELATE also extends naturally to dynamic scenes and generates videos of high visual fidelity.
arXiv Detail & Related papers (2020-07-02T17:27:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.