← Back to all news
arXiv Computer Vision By Chongbo Zhao, Jiangming Wang, Xilai Wang, Xinyu Wang, Jingyi Tang, Chunjie Hao, Pengjie Song, Yue Ma

Edit-VAR: Taming Visual Autoregressive Model for Precise Video Editing

Read the original on arXiv Computer Vision →

Edit‑VAR is a training‑free, inversion‑free framework that uses a pretrained visual autoregressive video model for text‑guided video editing. It encodes the source video into multi‑scale discrete tokens and applies probability‑guided conditional token replacement, attention‑guided token‑wise and scale‑aware modulation, and scale‑decoupled generation to preserve source appearance while enabling precise edits. The method also includes residual‑guided token pruning to reduce inference cost, and experimental results show it outperforms existing training‑free video editing methods in fidelity, source preservation, temporal coherence, and efficiency.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Aug 27

RefVideo-6M: A Reliable Reference-Based Dataset for Instructional Video Editing

RefVideo-6M is a new large-scale reference-guided editing dataset that includes 5 million video editing samples and 1 million image editing samples, each paired with about 6 million visual references. The dataset is constructed to avoid artifacts by using real, artifact‑free videos as targets and filtering input conditions with multiple editing experts, thereby providing reliable supervision. It enables models to learn fine‑grained visual correspondence beyond text‑only instructions and supports the training of a reference‑guided video editing model, Ref‑MoT, which shows improved visual quality, controllability, and reference consistency.

By Bojia Zi, Xiaoyan Yang, Yu Zhou, Ruijie Sun, Lihan Zhang, Bin Liang, Kam-Fai Wong, Haibin Huang, Chi Zhang, Xuelong Li
More like this →
arXiv Machine Learning
Aug 27

Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing

Memory-V2V is a memory‑augmented video‑to‑video diffusion framework designed to improve cross‑turn consistency in multi‑turn video editing. It stores previous outputs in an external memory, retrieves relevant edits, and incorporates them via relevance‑aware tokenization and adaptive compression, allowing scalable conditioning without linear computational growth. Experiments on iterative video novel view synthesis and text‑guided long video editing show that Memory‑V2V enhances consistency while preserving visual quality and outperforming strong baselines with modest overhead.

By Dohun Lee, Chun-Hao Paul Huang, Xuelin Chen, Jong Chul Ye, Duygu Ceylan, Hyeonho Jeong
diffusionnlp
More like this →