Dingkun Yan — accepted AI-conference papers

2026

Towards High-resolution and Disentangled Reference-based Sketch Colorization

Dingkun Yan, Xinrui Wang, Ru Wang, Zhuoru Li, Jinze Yu, Yusuke Iwasawa +2

CVPR 2026

Sketch colorization models have been widely studied to automate and assist in the creation of animation frames and digital illustrations. However, current methods are still not satisfactory for industrial standard applications in high-resolution synthesis and precise controllability of details. To f

Cited by 0 Source ↗code ↗Scholar ↗

2025

Image Referenced Sketch Colorization Based on Animation Creation Workflow

Dingkun Yan, Xinrui Wang, Zhuoru Li, Suguru Saito, Yusuke Iwasawa, Yutaka Matsuo +1

CVPR 2025poster

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 m…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗