Salvato in:
Dettagli Bibliografici
Autori principali: Cong, Xiaoyan, Yang, Haotian, Wang, Angtian, Wang, Yizhi, Yang, Yiding, Zhang, Canyu, Ma, Chongyang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2512.16906
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918255478702080
author Cong, Xiaoyan
Yang, Haotian
Wang, Angtian
Wang, Yizhi
Yang, Yiding
Zhang, Canyu
Ma, Chongyang
author_facet Cong, Xiaoyan
Yang, Haotian
Wang, Angtian
Wang, Yizhi
Yang, Yiding
Zhang, Canyu
Ma, Chongyang
contents Instruction-based video editing aims to modify an input video according to a natural-language instruction while preserving content fidelity and temporal coherence. However, existing diffusion-based approaches are often trained on paired data of simple editing operations, which fundamentally limits their ability to generalize to diverse and complex, real-world instructions. To address this generalization gap, we propose VIVA, a scalable framework for instruction-based video editing that leverages VLM-guided encoding and reward optimization. First, we introduce a VLM-based instructor that encodes the textual instruction, the first frame of the source video, and an optional reference image into visually-grounded instruction representations, providing fine-grained spatial and semantic context for the diffusion transformer backbone. Second, we propose a post-training stage, Edit-GRPO, which adapts Group Relative Policy Optimization to the domain of video editing, directly optimizing the model for instruction-faithful, content-preserving, and aesthetically pleasing edits using relative rewards. Furthermore, we propose a data construction pipeline designed to synthetically generate diverse, high-fidelity paired video-instruction data of basic editing operations. Extensive experiments show that VIVA achieves superior instruction following, generalization, and editing quality over state-of-the-art methods. Website: https://viva-paper.github.io
format Preprint
id arxiv_https___arxiv_org_abs_2512_16906
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VIVA: VLM-Guided Instruction-Based Video Editing with Reward Optimization
Cong, Xiaoyan
Yang, Haotian
Wang, Angtian
Wang, Yizhi
Yang, Yiding
Zhang, Canyu
Ma, Chongyang
Computer Vision and Pattern Recognition
Instruction-based video editing aims to modify an input video according to a natural-language instruction while preserving content fidelity and temporal coherence. However, existing diffusion-based approaches are often trained on paired data of simple editing operations, which fundamentally limits their ability to generalize to diverse and complex, real-world instructions. To address this generalization gap, we propose VIVA, a scalable framework for instruction-based video editing that leverages VLM-guided encoding and reward optimization. First, we introduce a VLM-based instructor that encodes the textual instruction, the first frame of the source video, and an optional reference image into visually-grounded instruction representations, providing fine-grained spatial and semantic context for the diffusion transformer backbone. Second, we propose a post-training stage, Edit-GRPO, which adapts Group Relative Policy Optimization to the domain of video editing, directly optimizing the model for instruction-faithful, content-preserving, and aesthetically pleasing edits using relative rewards. Furthermore, we propose a data construction pipeline designed to synthetically generate diverse, high-fidelity paired video-instruction data of basic editing operations. Extensive experiments show that VIVA achieves superior instruction following, generalization, and editing quality over state-of-the-art methods. Website: https://viva-paper.github.io
title VIVA: VLM-Guided Instruction-Based Video Editing with Reward Optimization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.16906