Video Object Insertion

Follow this topic Ask about this topic

Latest papers

11 papers2 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

UniVOE: A Removal-Driven Framework for Interaction-Aware Universal Video Object Editing
Oct 22, 2026Shuzhou Yang, Lanqing Guo, Lingen Li +4Video Object Insertion Video Editing
SECE, Peking University · Tencent Hunyuan · The Chinese University of Hong Kong
ALIVE: Interaction-Aligned Object Insertion for First-Frame-Guided Video Editing
Oct 6, 2026Zhenghong Zhou, Zhe Lin, Jiebo Luo +1Video Editing Instruction-Based Video Editing
University of Rochester · Adobe Research
Explicit Layer Modeling for Video Object Insertion and Video Layer Decomposition
Jul 28, 2026Kyujin Han, Seungjoo Shin, Sunghyun ChoVideo Diffusion Models Video Editing
POSTECH, Republic of Korea
AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance
May 31, 2026Xilong Zhou, Bao-Huy Nguyen, Zheng Zeng +6Video Editing Video Object Insertion
Max Planck Institute for Informatics · University of California Santa Barbara · NVIDIA Research +1
Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework
May 22, 2026Xiao Cao, Yansong Qu, Xiangzhen Chang +6Video Diffusion Models Video Editing
SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion
May 22, 2026Xinyu Chen, Yuyi Qian, Jiang Lin +9Video Diffusion Models Video Editing
1State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China · School of Intelligence Science and Technology, Nanjing University, Suzhou, China · 4Xi’an Jiaotong-Liverpool University +3
Controllable Video Object Insertion via Multiview Priors
Apr 16, 2026Xia Qi, Peishan Cong, Yichen Yao +3Video Editing Video Object Insertion
ShanghaiTech University
EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing
Mar 19, 2026Yang Fu, Yike Zheng, Ziyun Dai +1Video Object Insertion Object Removal
Institute of Big Data, College of Computer Science and Artificial Intelligence, Fudan University, China
Place-it-R1: Unlocking Environment-aware Reasoning Potential of MLLM for Video Object Insertion
Mar 6, 2026Bohai Gu, Taiyi Wu, Dazhao Du +5Video Object Insertion Video Editing
The Hong Kong University of Science and Technology · AI Technology Center, Tencent Video, Tencent · Peking University
PISCO: Precise Video Instance Insertion with Sparse Control
Feb 9, 2026Xiangbo Gao, Renjie Li, Xinghao Chen +4Physical Consistency in Video Generation Video Diffusion Models
Texas A&M University · KAIST · Stanford University +1
InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion
Dec 19, 2025Hoiyeong Jin, Hyojin Jang, Junha Hyung +6Video Diffusion Models Video Editing
KAIST AI · SK Telecom

Oct 22, 2026J/K move · Enter open · S save

UniVOE: A Removal-Driven Framework for Interaction-Aware Universal Video Object Editing

Shuzhou Yang, Lanqing Guo, Lingen Li, Weiqi Li+3

SECE, Peking University · Tencent Hunyuan · The Chinese University of Hong Kong

Video Object Insertion Video Editing

Open paper AskPDF arXiv

Video object removal and injection are reciprocal editing operations between object-present and object-absent video states, yet they differ substantially in training difficulty. Removal can be effectively bootstrapped from video inpainting and further adapted to erase object-related interaction effects. Injection, however, requires large-scale paired supervision to model object appearance, dynamics, and scene-dependent effects, while perfectly aligned real-world pairs are difficult to collect and synthetic data lacks sufficient realism and diversity. To address this challenge, we present UniVOE, a removal-driven framework for training both video object removal and injection models. We first train an effect-aware remover by transferring video inpainting priors and finetuning on object-present/object-absent pairs. The trained remover converts real object-present videos into object-absent counterparts, creating large-scale paired supervision for injection. An injection model is trained on these pairs in the reverse direction to recover objects together with their dynamics and interaction effects. Moreover, since pixel-level reconstruction alone cannot adequately capture perceptual realism, we introduce a reward-based post-training method that aligns injection results with human preferences using a proprietary reward model. Experiments against strong open-source and commercial systems demonstrate that UniVOE achieves state-of-the-art performance on both object removal and injection, particularly in challenging interaction-effect cases.