ECCV 2026 논문 채택: Semantic Line DiffusionECCV2026 Accepted: Semantic Line Diffusion

논문 「Semantic Line Diffusion: Character-Consistent Line Art from Text-Annotated Storyboards」가 European Conference on Computer Vision 2026 (ECCV 2026)에 채택되었습니다.

이 연구는 텍스트가 주석으로 달린 거친 스토리보드 스케치에서 깔끔하고 캐릭터 일관성이 유지되는 선화를 생성하는 diffusion transformer 프레임워크 PanelDiff를 제안합니다. 다중 참조 캐릭터 조건화, 메모리 증강 표현 뱅크, 패널 인식 diffusion transformer를 결합하여 선화의 충실도, 캐릭터 정체성 보존, 패널 간 일관성을 높입니다.

저자:

• 최서연
• 이경수 (교신저자)

Top BK/CS 학술대회에 채택된 것을 축하하며, 웹툰 및 스토리보드 제작을 위한 캐릭터 일관성 생성 모델링에 기여한 저자들에게 축하를 전합니다.

관련 링크:

• Semantic Line Diffusion: Character-Consistent Line Art from Text-Annotated Storyboards

We are pleased to announce that our paper, “Semantic Line Diffusion: Character-Consistent Line Art from Text-Annotated Storyboards,” has been accepted to the European Conference on Computer Vision 2026 (ECCV 2026).

This work presents PanelDiff, a diffusion transformer framework for generating clean, character-consistent line art from rough, text-annotated storyboard sketches. The framework combines multi-reference character conditioning, a memory-augmented representation bank, and a panel-aware diffusion transformer to improve line-art fidelity, identity preservation, and cross-panel consistency.

Authors:

• Seo-Yeon Choi
• Kyungsu Lee (corresponding author)

This paper was accepted to a Top BK/CS conference. Congratulations to the authors on this meaningful contribution to character-consistent generative modeling for webtoon and storyboard production.

Related link:

• Semantic Line Diffusion: Character-Consistent Line Art from Text-Annotated Storyboards