IDAG-Edit: Multi-Object Video Editing via Instance-Decoupled Attention and Guidance
- URL: http://arxiv.org/abs/2606.22042v1
- Date: Sat, 20 Jun 2026 13:47:39 GMT
- Title: IDAG-Edit: Multi-Object Video Editing via Instance-Decoupled Attention and Guidance
- Abstract summary: IDAGEdit is a training-free framework for fine-grained multi-object video editing with strong temporal consistency.<n>Our method improves temporal stability and multi-object controllability over state-of-the-art video editing approaches.
- Score: 26.00049090733744
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Diffusion-based video editing has made significant progress; however, achieving precise and temporally consistent object-level control, especially in multi-object scenarios, remains challenging due to attention leakage, identity drift, and unstable temporal dynamics. In this work, we propose IDAGEdit, a training-free framework for fine-grained multi-object video editing with strong temporal consistency. The framework adopts Layout-guided Attention Modulation to facilitate coherent multi-object editing, while Instance-level Masks are introduced to preserve individual object identity and enforce localized attention within each object region, thereby enabling fine-grained, object-level editing. Extensive qualitative and quantitative evaluations demonstrate that our method improves temporal stability and multi-object controllability over state-of-the-art video editing approaches.
Related papers
- Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning [56.17582599802973]
We introduce the Multi-Instruction Multi-Shot Long-Video Editing (MMLVE) task, which is structured around three core objectives.<n>To tackle these three unique challenges, we introduce an agentic editing framework that leverages the Large Language Models (LLMs) and Vision-Language Models (VLMs)<n>Extensive experiments demonstrate that our MMLVE-Agent outperforms existing closed-source SOTA approaches.
arXiv Detail & Related papers (2026-08-27T08:48:13Z) - MSEditor: Toward Consistent Multi-Shot Video Editing [46.964066826513374]
We propose MSEditor, the first framework designed specifically for consistent multi-shot video editing.<n>To overcome the scarcity of high-quality multi-shot training data, we repurpose existing multi-view video datasets to provide robust cross-shot supervision.<n>To effectively mitigate cumulative errors and ensure long-range temporal coherence, we design a Cross-Shot Packing strategy.
arXiv Detail & Related papers (2026-08-18T09:21:58Z) - Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing [53.06890499054828]
We propose an occlusion-aware selection framework that automatically identifies an optimal anchor frame for downstream editing.<n>Our framework enables precise and temporally consistent editing without requiring manual annotations.
arXiv Detail & Related papers (2026-05-22T03:19:24Z) - MLV-Edit: Towards Consistent and Highly Efficient Editing for Minute-Level Videos [4.3184511910208325]
MLV-Edit is a training-free, flow-based framework for minute-level video editing.<n>It employs a divide-and-conquer strategy for segment-wise editing, facilitated by two core modules.<n>It consistently outperforms state-of-the-art methods in terms of temporal stability and semantic fidelity.
arXiv Detail & Related papers (2026-02-02T14:07:00Z) - ConsistEdit: Highly Consistent and Precise Training-free Visual Editing [17.162316662697965]
We propose ConsistEdit, a novel attention control method specifically tailored for MM-DiT.<n>It incorporates vision-only attention control, mask-guided pre-attention fusion, and differentiated manipulation of the query, key, and value tokens.<n>It achieves state-of-the-art performance across a wide range of image and video editing tasks, including both structure-consistent and structure-inconsistent scenarios.
arXiv Detail & Related papers (2025-10-20T17:59:52Z) - O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing [88.93410369258203]
O-DisCo-Edit is a unified framework that incorporates a novel object distortion control (O-DisCo)<n>This signal, based on random and adaptive noise, flexibly encapsulates a wide range of editing cues within a single representation.<n>O-DisCo-Edit enables efficient, high-fidelity editing through an effective training paradigm.
arXiv Detail & Related papers (2025-09-01T16:29:39Z) - MAKIMA: Tuning-free Multi-Attribute Open-domain Video Editing via Mask-Guided Attention Modulation [55.101611012677616]
Diffusion-based text-to-image (T2I) models have demonstrated remarkable results in global video editing tasks.<n>We present MAKIMA, a tuning-free MAE framework built upon pretrained T2I models for open-domain video editing.
arXiv Detail & Related papers (2024-12-28T02:36:51Z) - DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes [23.215760822443194]
DriveEditor is a diffusion-based framework for object editing in driving videos.<n>It offers a unified framework for comprehensive object editing operations, including repositioning, replacement, deletion, and insertion.
arXiv Detail & Related papers (2024-12-27T04:49:36Z) - VIA: Unified Spatiotemporal Video Adaptation Framework for Global and Local Video Editing [91.60658973688996]
We introduce VIA, a unified Video Adaptation framework for global local video editing, pushing the limits of consistently editing minute-long videos.<n>To ensure local consistency within individual frames, we designed test-time editing adaptation to adapt a pre-trained image editing model.<n>We show that VIA can achieve consistent long video editing in minutes, unlocking the potential for advanced video editing tasks over long video sequences.
arXiv Detail & Related papers (2024-06-18T17:51:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.