TY - GEN
T1 - Animation Super-Resolution via Explicit Line Art Structure Loss
AU - Jing, Minghao
AU - Wang, Chongwen
N1 - Publisher Copyright:
© 2026 Copyright held by the owner/author(s).
PY - 2026/9/1
Y1 - 2026/9/1
N2 - This paper proposes an optimization framework for animation super-resolution (ASR) to address line art structural collapse. Current state-of-the-art (SOTA) methods rely heavily on implicit supervision and often fail to preserve line integrity. To solve this, we introduce an explicit line art structure loss. Unlike prior approaches working solely in pixel or semantic domains, our loss directly constrains the geometric attributes of lines which explicitly ensures their sharpness and topological continuity. Specifically, our method integrates a differentiable, adaptive-threshold Soft XDoG operator and combine this with gradient profile priors (GPP) and gradient orientation consistency to guide the reconstruction. Experiments on the API dataset demonstrate the effectiveness of our approach. It significantly outperforms existing methods in maintaining line integrity and structural preservation.
AB - This paper proposes an optimization framework for animation super-resolution (ASR) to address line art structural collapse. Current state-of-the-art (SOTA) methods rely heavily on implicit supervision and often fail to preserve line integrity. To solve this, we introduce an explicit line art structure loss. Unlike prior approaches working solely in pixel or semantic domains, our loss directly constrains the geometric attributes of lines which explicitly ensures their sharpness and topological continuity. Specifically, our method integrates a differentiable, adaptive-threshold Soft XDoG operator and combine this with gradient profile priors (GPP) and gradient orientation consistency to guide the reconstruction. Experiments on the API dataset demonstrate the effectiveness of our approach. It significantly outperforms existing methods in maintaining line integrity and structural preservation.
KW - Animation super-resolution
KW - explicit supervision
KW - gradient profile prior
KW - line art structure
UR - https://www.scopus.com/pages/publications/105050192675
U2 - 10.1145/3821966.3822004
DO - 10.1145/3821966.3822004
M3 - Conference contribution
AN - SCOPUS:105050192675
T3 - Proceedings of 2026 3rd International Conference on Innovation Management and Information Systems, ICIIS 2026
SP - 226
EP - 230
BT - Proceedings of 2026 3rd International Conference on Innovation Management and Information Systems, ICIIS 2026
PB - Association for Computing Machinery, Inc
T2 - 2026 3rd International Conference on Innovation Management and Information Systems, ICIIS 2026
Y2 - 27 March 2026 through 29 March 2026
ER -