用参考图实现动漫上色，让颜色更准、画面更连贯。
AnimeColor: Reference-based Animation Colorization with Diffusion Transformers
- 基于扩散变换器，结合草图和参考图生成上色动画。
- 引入高层颜色提取与低层颜色引导，提升色彩准确性和细节还原。
- 适合动漫工业界使用，支持高一致性与高质量输出。
动画上色在动画制作中至关重要，但现有方法难以兼顾色彩准确性与时序一致性。为此，我们提出AnimeColor，一种基于参考图的动画上色框架，采用扩散变换器（DiT）构建视频扩散模型。该方法将草图序列融入模型，实现草图控制的动画生成。设计了两个核心组件：高层颜色提取器（HCE）用于捕捉语义级颜色信息，低层颜色引导器（LCG）用于从参考图像中提取精细颜色细节，二者协同指导视频扩散过程。此外，采用多阶段训练策略以最大化利用参考图像中的颜色信息。大量实验表明，AnimeColor在色彩准确性、草图对齐度、时序一致性和视觉质量方面均优于现有方法。本框架不仅推动了动画上色技术的前沿进展，也为工业应用提供了实用解决方案。代码将公开于https://github.com/IamCreateAI/AnimeColor。
原文摘要 · Abstract (English)
Animation colorization plays a vital role in animation production, yet existing methods struggle to achieve color accuracy and temporal consistency. To address these challenges, we propose \textbf{AnimeColor}, a novel reference-based animation colorization framework leveraging Diffusion Transformers (DiT). Our approach integrates sketch sequences into a DiT-based video diffusion model, enabling sketch-controlled animation generation. We introduce two key components: a High-level Color Extractor (HCE) to capture semantic color information and a Low-level Color Guider (LCG) to extract fine-grained color details from reference images. These components work synergistically to guide the video diffusion process. Additionally, we employ a multi-stage training strategy to maximize the utilization of reference image color information. Extensive experiments demonstrate that AnimeColor outperforms existing methods in color accuracy, sketch alignment, temporal consistency, and visual quality. Our framework not only advances the state of the art in animation colorization but also provides a practical solution for industrial applications. The code will be made publicly available at \href{https://github.com/IamCreateAI/AnimeColor}{https://github.com/IamCreateAI/AnimeColor}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。