Paint Bucket Colorization Using Anime Character Color Design Sheets

TL;DR

This work introduces inclusion matching, which allows the network to understand the inclusion relationships between segments, rather than relying solely on direct visual correspondences, and significantly improves performance in both keyframe colorization and consecutive frame colorization.

Abstract

Line art colorization plays a crucial role in hand-drawn animation production, where digital artists manually colorize segments using a paint bucket tool, guided by RGB values from character color design sheets. This process, often called paint bucket colorization, involves two main tasks: keyframe colorization, where colors are applied according to the character's color design sheet, and consecutive frame colorization, where these colors are replicated across adjacent frames. Current automated colorization methods primarily focus on reference-based and segment-matching approaches. However, reference-based methods often fail to accurately assign specific colors to each region, while matching-based methods are limited to consecutive frame colorization and struggle with issues like significant deformation and occlusion. In this work, we introduce inclusion matching, which allows the network to understand the inclusion relationships between segments, rather than relying solely on direct visual correspondences. By integrating this approach with segment parsing and color warping modules, our inclusion matching pipeline significantly improves performance in both keyframe colorization and consecutive frame colorization. To support our network's training, we have developed a unique dataset named PaintBucket-Character, which includes rendered line arts alongside their colorized versions and shading annotations for various 3D characters. To replicate industry animation data formats, we also created color design sheets for each character, with semantic information for each color and standard pose reference images. Experiments highlight the superiority of our method, demonstrating accurate and consistent colorization across both our proposed benchmarks and hand-drawn animations.

Figures (22)

• Figure 1: In animation production, digital painters refer to the character color design sheet and use the paint bucket tool to colorize drawn line art frame by frame. This character color design sheet includes a text-color list, which provides a text description along with highlight, normal, and shadow colors for each semantic element of the character. To automate this process, we propose a keyframe colorization method and a consecutive frames colorization method. Our keyframe colorization approach can colorize the keyframe line arts in different poses and perspectives based on a given character color design sheet. Then, the consecutive frames colorization method can propagate these colors throughout the sequence to achieve automatic paint bucket colorization. ©Drawn by NeonRed, used with artist's permission.
• Figure 2: Production procedure of the hand-drawn animation. Animators pre-colorize regions such as highlights and shadows while using different colors to differentiate regions of hair, skin, and others in the clean-up stage. These colors, known as shading annotations, serve as guides for digital painters, helping prevent confusion during the coloring process. ©drawn by Nicca (Sriprachum Kongwisawamit), used with artist permission.
• Figure 3: Several examples of our rendered characters in PaintBucket-Character dataset.
• Figure 4: Overview of our synthetic data generation pipeline. We extract the UV map (a) from the character. Then, we use a paint bucket tool to fill the occupied UV region, creating color label (b) and index label (c). Label images (b) and (c) are then pasted back to the 3D meshes to create flat color characters (d) and (e), respectively. Finally, we post-process the index image (e) to obtain the rendered line art image (f).
• Figure 5: Our data generation pipeline for (a) the color design sheet and (b) ground truth and model input with shading annotations. In particular, we use 'Hh, Hs, Ho, Sh, Ss, So' as shading annotations to indicate the highlight and shadow regions of hair, skin, and others.