SOURCE-LINKED INTELLIGENCE

GraLoD: Graphics-Inspired Continuous Level-of-Detail Learning for Image Restoration

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

The spatial support required for image restoration varies across degradation types, image regions, and reconstruction stages. However, most existing methods rely on predefined multi-scale hierarchies and aggregate features through fixed fusion or attention, leaving the representation scale itself largely determined by the network architecture. This limitation becomes more pronounced when a task-specific backbone is extended to heterogeneous degradations in all-in-one restoration. Inspired by level-of-detail (LOD) rendering in computer graphics, we propose GraLoD, a plug-and-play framework that

Read original source ↗ Open in workspace

recordType

paper

region

Global