Image Referenced Sketch Colorization Based on Animation Creation Workflow

TL;DR

This paper introduces a diffusion-based sketch colorization framework inspired by animation workflows, effectively using spatial guidance and RGB references to produce artifact-free, high-quality colorized images with independent foreground and background control.

Contribution

The proposed method uniquely integrates spatial masks and a split cross-attention mechanism with LoRA modules, enabling independent foreground and background colorization and artifact elimination.

Findings

Outperforms existing methods in artifact-free, high-quality colorization

Effectively handles geometric mismatched references

Demonstrates robustness through extensive experiments and user studies

Abstract

Sketch colorization plays an important role in animation and digital illustration production tasks. However, existing methods still meet problems in that text-guided methods fail to provide accurate color and style reference, hint-guided methods still involve manual operation, and image-referenced methods are prone to cause artifacts. To address these limitations, we propose a diffusion-based framework inspired by real-world animation production workflows. Our approach leverages the sketch as the spatial guidance and an RGB image as the color reference, and separately extracts foreground and background from the reference image with spatial masks. Particularly, we introduce a split cross-attention mechanism with LoRA (Low-Rank Adaptation) modules. They are trained separately with foreground and background regions to control the corresponding embeddings for keys and values in cross-attention. This design allows the diffusion model to integrate information from foreground and background independently, preventing interference and eliminating the spatial artifacts. During inference, we design switchable inference modes for diverse use scenarios by changing modules activated in the framework. Extensive qualitative and quantitative experiments, along with user studies, demonstrate our advantages over existing methods in generating high-qualigy artifact-free results with geometric mismatched references. Ablation studies further confirm the effectiveness of each component. Codes are available at https://github.com/ tellurion-kanata/colorizeDiffusion.