Towards Automated 2D Character Animation

Simple item page
dc.contributor.authorMailee, Hamilaen_US
dc.contributor.authorAnjos, Rafael Kuffner dosen_US
dc.contributor.editorBerio, Danielen_US
dc.contributor.editorBruckert, Alexandreen_US
dc.date.accessioned2025-05-09T09:43:48Z
dc.date.available2025-05-09T09:43:48Z
dc.date.issued2025
dc.description.abstractAutomating facial expression changes in comics and 2D animation presents several challenges, as facial structures can vary widely, and audiences are susceptible to the subtlest changes. Building on extensive research in human face image manipulation, landmark-guided image editing offers a promising solution, providing precise control and yielding satisfactory results. This study addresses the challenges hindering the advancement of landmark-based methods for cartoon characters and proposes the use of object detection models -specifically YOLOX and Faster R-CNN- to detect initial facial regions. These detections serve as a foundation for expanding landmark annotations, enabling more effective expression manipulation to animate expressive characters. The codes and trained models are publicly available here.en_US
dc.description.sectionheadersPosters
dc.description.seriesinformationACM/EG Expressive Symposium - WICED: Eurographics Workshop on Intelligent Cinematography and Editing - Artworks, Posters, Demos
dc.identifier.doi10.2312/exw.20251067
dc.identifier.isbn978-3-03868-272-1
dc.identifier.pages4 pages
dc.identifier.urihttps://doi.org/10.2312/exw.20251067
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/exw20251067
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Interest point and salient region detections; Object detection
dc.subjectComputing methodologies → Interest point and salient region detections
dc.subjectObject detection
dc.titleTowards Automated 2D Character Animationen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
exw20251067.pdf
Size:
8.81 MB
Format:
Adobe Portable Document Format
Download
Collections
Expressive + WICED 2025
Expressive + WICED 2025: Artworks, Posters, and Demo