Uni-Animator: Towards Unified Visual Colorization

TL;DR

Uni-Animator is a unified diffusion transformer framework that significantly improves image and video sketch colorization by enhancing reference alignment, detail preservation, and temporal coherence.

Contribution

It introduces a novel unified approach with reference enhancement, physical detail reinforcement, and motion-aware encoding for improved colorization across domains.

Findings

Achieves competitive results on both image and video sketch colorization.

Effectively preserves high-frequency physical details.

Maintains robust temporal consistency in videos.

Abstract

We propose Uni-Animator, a novel Diffusion Transformer (DiT)-based framework for unified image and video sketch colorization. Existing sketch colorization methods struggle to unify image and video tasks, suffering from imprecise color transfer with single or multiple references, inadequate preservation of high-frequency physical details, and compromised temporal coherence with motion artifacts in large-motion scenes. To tackle imprecise color transfer, we introduce visual reference enhancement via instance patch embedding, enabling precise alignment and fusion of reference color information. To resolve insufficient physical detail preservation, we design physical detail reinforcement using physical features that effectively capture and retain high-frequency textures. To mitigate motion-induced temporal inconsistency, we propose sketch-based dynamic RoPE encoding that adaptively models motion-aware spatial-temporal dependencies. Extensive experimental results demonstrate that Uni-Animator achieves competitive performance on both image and video sketch colorization, matching that of task-specific methods while unlocking unified cross-domain capabilities with high detail fidelity and robust temporal consistency.