Learning Inclusion Matching for Animation Paint Bucket Colorization

https://ykdai.github.io/projects/InclusionMatching Reference frame Target frame AnT (AnimeRun) RAFT (AnimeRun) AnT (Cadmium) Ours Ground truth Figure 1. In the animation industry, digital painters use paint bucket tool to colorize drawn line arts frame by frame. Our proposed pipeline streamlines this process by requiring the painters to colorize just one frame, after which the algorithm autonomously propagates the color to subsequent frames, enabling automatic colorization. Compared with optical-flow-based method RAFT [35] and segment-matching-based method AnT [8], our method can achieve more robust results on challenging cases such as one-to-many matching, large deformation, and tiny region colorization. In this figure, RAFT is trained on Sintel dataset [5] and finetuned on AnimeRun [30]. We use the most frequent color in each segment to colorize each line-enclosed region. ©drawn by Nicca (Sriprachum Kongwisawamit), used with artist permission.