paper-with-me

홈 › Papers

MLV-Edit: Towards Consistent and Highly Efficient Editing for Minute-Level Videos

2026-02-02 · Yangyi Cao, Yuanhang Li, Lan Chen, Qi Mao arxiv

We propose MLV-Edit, a training-free, flow-based framework that address the unique challenges of minute-level video editing. While existing techniques excel in short-form video manipulation, scaling them to long-duration videos remains challenging due to prohibitive computational overhead and the difficulty of maintaining global temporal consistency across thousands of frames. To address this, MLV-Edit employs a divide-and-conquer strategy for segment-wise editing, facilitated by two core modules: Velocity Blend rectifies motion inconsistencies at segment boundaries by aligning the flow fields of adjacent chunks, eliminating flickering and boundary artifacts commonly observed in fragmented video processing; and Attention Sink anchors local segment features to global reference frames, effectively suppressing cumulative structural drift. Extensive quantitative and qualitative experiments demonstrate that MLV-Edit consistently outperforms state-of-the-art methods in terms of temporal stability and semantic fidelity.

📄 PDF Abstract BibTeX arXiv:2602.02123

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

VIA: Unified Spatiotemporal Video Adaptation Framework for Global and Local Video Editing

2024-06-18 · Jing Gu, Yuwei Fang, Ivan Skorokhodov, Peter Wonka 외

Video editing serves as a fundamental pillar of digital media, spanning applications in entertainment, education, and professional communication. However, previous methods often overlook the necessity of comprehensively …

Video Editing

Efficient-NeRF2NeRF: Streamlining Text-Driven 3D Editing with Multiview Correspondence-Enhanced Diffusion Models

2023-12-13 · Liangchen Song, Liangliang Cao, Jiatao Gu, Yifan Jiang 외

The advancement of text-driven 3D content editing has been blessed by the progress from 2D generative diffusion models. However, a major obstacle hindering the widespread adoption of 3D content editing is its time-intens…

GPU

Omni-3DEdit: Generalized Versatile 3D Editing in One-Pass

2026-03-18 · Chen Liyi, Wang Pengfei, Zhang Guowen, Ma Zhiyuan 외 arxiv

Most instruction-driven 3D editing methods rely on 2D models to guide the explicit and iterative optimization of 3D representations. This paradigm, however, suffers from two primary drawbacks. First, it lacks a universal…

Physics-Aware 3D Gaussian Editing for Driving Scene Generation

2026-05-25 · Feng Zhou, Jian Zhang, Yuhang Sun, He Wang 외 arxiv

3D Gaussian Splatting (3DGS) has shown great potential in autonomous driving simulation and data generation, enabling photorealistic reconstruction and flexible scene manipulation. However, existing 3DGS scene editing me…

Autonomous DrivingScene Generation

3DGS-Drag: Dragging Gaussians for Intuitive Point-Based 3D Editing

2026-01-12 · Jiahua Dong, Yu-Xiong Wang arxiv

The transformative potential of 3D content creation has been progressively unlocked through advancements in generative models. Recently, intuitive drag editing with geometric changes has attracted significant attention i…