Cover Image

From Understanding to Erasing: Towards Complete and Stable Video Object Removal

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Dingming, Wang, Wenjing, Li, Chen, Lyu, Jing
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AdaEraser: Training-Free Object Removal via Adaptive Attention Suppression
by: Liu, Dingming
Published: (2026)

EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing
by: Fu, Yang, et al.
Published: (2026)

Identity as Presence: Towards Appearance and Voice Personalized Joint Audio-Video Generation
by: Chen, Yingjie, et al.
Published: (2026)

From Ideal to Real: Stable Video Object Removal under Imperfect Conditions
by: Hu, Jiagao, et al.
Published: (2026)

Video Generation with Stable Transparency via Shiftable RGB-A Distribution Learner
by: Dong, Haotian, et al.
Published: (2025)

Erase Diffusion: Empowering Object Removal Through Calibrating Diffusion Pathways
by: Liu, Yi, et al.
Published: (2025)

EraseDraw: Learning to Draw Step-by-Step via Erasing Objects from Images
by: Canberk, Alper, et al.
Published: (2024)

Bi-Erasing: A Bidirectional Framework for Concept Removal in Diffusion Models
by: Chen, Hao, et al.
Published: (2025)

EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal
by: Jo, Sanghyun, et al.
Published: (2025)

Learning Stochastic Bridges for Video Object Removal via Video-to-Video Translation
by: Lou, Zijie, et al.
Published: (2026)

Concept Corrector: Erase concepts on the fly for text-to-image diffusion models
by: Meng, Zheling, et al.
Published: (2025)

EarlyTom: Early Token Compression Completes Fast Video Understanding
by: Wang, Hesong, et al.
Published: (2026)

MagicEraser: Erasing Any Objects via Semantics-Aware Control
by: Li, Fan, et al.
Published: (2024)

LaRender: Training-Free Occlusion Control in Image Generation via Latent Rendering
by: Zhan, Xiaohang, et al.
Published: (2025)

MiniMax-Remover: Taming Bad Noise Helps Video Object Removal
by: Zi, Bojia, et al.
Published: (2025)

Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video
by: Tan, Yuting, et al.
Published: (2026)

T2VUnlearning: A Concept Erasing Method for Text-to-Video Diffusion Models
by: Ye, Xiaoyu, et al.
Published: (2025)

Erasing Undesirable Influence in Diffusion Models
by: Wu, Jing, et al.
Published: (2024)

PROBE: Diagnosing Residual Concept Capacity in Erased Text-to-Video Diffusion Models
by: Xie, Yiwei, et al.
Published: (2026)

StableWorld: Towards Stable and Consistent Long Interactive Video Generation
by: Yang, Ying, et al.
Published: (2026)

VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing
by: Chang, Zhiyuan, et al.
Published: (2024)

Object-WIPER : Training-Free Object and Associated Effect Removal in Videos
by: Kushwaha, Saksham Singh, et al.
Published: (2026)

Towards Stable 3D Object Detection
by: Wang, Jiabao, et al.
Published: (2024)

How Can Objects Help Video-Language Understanding?
by: Tang, Zitian, et al.
Published: (2025)

Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation
by: Xue, Bowen, et al.
Published: (2025)

High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net
by: Li, Zinuo, et al.
Published: (2023)

VidText: Towards Comprehensive Evaluation for Video Text Understanding
by: Yang, Zhoufaran, et al.
Published: (2025)

View-consistent Object Removal in Radiance Fields
by: Lu, Yiren, et al.
Published: (2024)

GenEraser: Generalizable Video Object Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver
by: Chen, Yuqing, et al.
Published: (2026)

Towards 3D Object-Centric Feature Learning for Semantic Scene Completion
by: Wang, Weihua, et al.
Published: (2025)

Towards Long Video Understanding via Fine-detailed Video Story Generation
by: You, Zeng, et al.
Published: (2024)

YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal
by: Wu, Chenyang, et al.
Published: (2026)

You Only Erase Once: Erasing Anything without Bringing Unexpected Content
by: Zhu, Yixing, et al.
Published: (2026)

ROSE: Remove Objects with Side Effects in Videos
by: Miao, Chenxuan, et al.
Published: (2025)

GeoRemover: Removing Objects and Their Causal Visual Artifacts
by: Zhu, Zixin, et al.
Published: (2025)

MedHorizon: Towards Long-context Medical Video Understanding in the Wild
by: Du, Bodong, et al.
Published: (2026)

OmniEraser: Remove Objects and Their Effects in Images with Paired Video-Frame Data
by: Wei, Runpu, et al.
Published: (2025)

Completing Visual Objects via Bridging Generation and Segmentation
by: Li, Xiang, et al.
Published: (2023)

SECURE: Stable Early Collision Understanding via Robust Embeddings in Autonomous Driving
by: Wang, Wenjing, et al.
Published: (2026)

ObjEmbed: Towards Universal Multimodal Object Embeddings
by: Fu, Shenghao, et al.
Published: (2026)