Presentation

<
Cobra: Efficient Line Art COlorization with BRoAder References
SessionDo it With Style & Fashion
DescriptionCobra is a novel efficient long-context fine-grained ID preservation framework for line art colorization, achieving high precision, efficiency, and flexible usability for comic colorization. By effectively integrating extensive contextual references, it transforms black-and-white line art into vibrant illustrations.
Authors
Junhao Zhuang
Tsinghua University
Lingen Li
Chinese University of Hong Kong
Xuan Ju
Chinese University of Hong Kong
Zhaoyang Zhang
Chinese University of Hong Kong
Chun Yuan
Tsinghua University
Ying Shan
Tencent
Event Type
Technical Paper
TimeTuesday, 12 August 20252:50pm - 3:00pm PDT
LocationWest Building, Rooms 118-120
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Tuesday, 12 August 20252:00pm - 3:30pm PDTWest Building, Rooms 118-120
Recordings
Livestreamed
Recorded
Next PresentationNext PresentationDo it With Style & Fashion - Interactive Discussion
Similar Presentations
ColorSurge: Bringing Vibrancy and Efficiency to Automatic Video Colorization via Dual-Branch Fusion
VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control
40. Confidence Estimation of Few-Shot Patch-Based Learning for Anime-Style Colorization