arXiv cs.AI· Yuxuan Chen, Feng Xie, Jiagao Hu, Fuhao Li, Zepeng Wang, Fei Wang, Daiguo Zhou·· 2 天前AI 评分29
LociArt：自由风格局部视频风格化的统一范式
LociArt: A Unified Paradigm for Free-Style Local Video Stylization
AI 导读
LociArt 提出面向自由风格局部视频风格化的统一范式，核心方法 GRNStyle 基于 Generative Refinement Networks（GRN）引入极坐标风格感知掩码，将风格身份编码为等范数方向，并配合表示—几何条件实现时空上下文与几何控制。
正文 · 原文
Abstract:Video stylization typically transforms entire scenes, while local artistic editing requires precise region--style association, spatial control, and temporal consistency. We introduce LociArt, a unified paradigm for free-style local video stylization that explicitly specifies where to stylize and what style to apply while preserving non-target content. At its core, GRNStyle builds on Generative Refinement Networks (GRN) and introduces a polar style-aware mask that embeds style identities as equal-norm directions within selected regions. Complementary representation--geometry conditioning combines encoded mask features with raw-mask spatial support, integrating spatiotemporal context with geometric control. To provide paired supervision, we develop an automated pipeline combining global stylization, video object removal, matting, and compositing, and construct the LociArt-100K Dataset with 100K local stylization pairs. We further establish the LociArt Benchmark, comprising 80 source videos and 84 target masks covering 168 foreground/background stylization cases, with a Style Prototype Similarity (SPS) evaluation scheme for regional style quality and complementary measures of non-target preservation and temporal consistency. Experiments show that GRNStyle outperforms existing methods in regional style quality and spatial control while maintaining strong temporal consistency. Qualitative examples further illustrate joint stylization of multiple regions with the same or different learned styles, despite training only on single-region, single-style pairs. Together, these components provide a unified foundation for learning and evaluating controllable local video stylization. Project page: this https URL.
| Comments: | Project page: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Multimedia (cs.MM) |
| Cite as: | arXiv:2610.36456 [cs.CV] |
| (or arXiv:2610.36456v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36456 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiagao Hu [view email]
[v1]
Tue, 27 Oct 2026 01:04:39 UTC (12,749 KB)
来源：arXiv cs.AI · arxiv.org