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

2026-09-14

AI Summary

为解决图像恢复中不同退化类型、区域及阶段所需空间支持不同的问题，GraLoD通过引入连续层级细节学习方法自适应调整恢复尺度。

Abstract

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 treats restoration scale as a spatially varying and stage-dependent continuous variable. GraLoD reuses the native encoder hierarchy, aligns its multi-scale features into a shared LOD representation space, and predicts a stage-conditioned LOD field at each decoder stage. Each spatial location then continuously queries only two neighboring representation levels, enabling the effective restoration scale to adapt to both local image content and reconstruction progress. To prevent degenerate or arbitrary scale selection, we further introduce minimal-sufficient footprint calibration (MSFC) together with structure-aware regularization (SAR) to encourage restoration-effective and spatially coherent LOD assignments. GraLoD can be directly integrated into existing restoration backbones without redesigning their fundamental feature-processing blocks. Extensive experiments demonstrate consistent improvements in task-specific and all-in-one restoration.

Problem

• image restoration
• multi-scale hierarchies
• level-of-detail (LOD)
• heterogeneous degradations

Innovation

• level-of-detail (LOD)
• spatially varying and stage-dependent
• minimal-sufficient footprint calibration (MSFC)
• structure-aware regularization (SAR)