SIGGRAPH Asia 2025 Home
Explore the Full Program of SIGGRAPH Asia 2025!
Close

Presentation

Fisheye Patch-Based Automatic Colorization Method for Anime Line-drawings
SessionPosters
DescriptionOur fisheye patch structure efficiently incorporates global context in patch-based learning by compressing surroundings while preserving central detail, achieving accurate and consistent colorization of anime line drawings.
Contributors
Ryosuke Takamura
Chiba University
Taiki Watanabe
Chiba University
Akinobu Maejima
OLM Digital, Inc. IMAGICA GROUP Inc.
Seitaro Shinagawa
Nara Institute of Science and Technology (NAIST)
Takuya Funatomi
Kyoto University
Nara Institute of Science and Technology
Yasuhiro Mukaigawa
Nara Institute of Science and Technology (NAIST)
Shigeo Morishima
Waseda University
Hiroyuki Kubo
Chiba University
Event Type
Poster
TimeTuesday, 16 December 20259:00am - 6:00pm HKT
LocationHall 3F/G Concourse, Level 3
Registration Categories
Next PresentationNext Presentation
Improving Angular Parameterization for Compact Neural Materials
Similar Presentations
LayerPack: Training-Free Animation Inbetweening with Cross-Layer Consistency
ChromaFlow: End-to-End Flow Matching for Efficient Video Colorization
An Abstract Form Guided Method for Image Generation without Training