GraLoD：面向图像恢复的图形学启发连续细节层次学习
GraLoD: Graphics-Inspired Continuous Level-of-Detail Learning for Image Restoration
- Shanghai Jiao Tong University（上海交通大学）
- Harbin Institute of Technology（哈尔滨工业大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对图像恢复中尺度选择受限于网络架构的问题，提出图形学启发的连续细节层次学习框架GraLoD，通过预测连续LOD场并引入校准与正则化，即插即用地提升任务特定及全能恢复性能。
AI中文摘要：
图像恢复所需的空间支持因退化类型、图像区域和重建阶段而异。然而，现有方法大多依赖预定义的多尺度层级，并通过固定融合或注意力机制聚合特征，导致表示尺度本身在很大程度上由网络架构决定。当任务特定的骨干网络扩展到全能恢复中的异构退化时，这一局限性变得更加明显。受计算机图形学中细节层次（LOD）渲染的启发，我们提出了GraLoD，一个即插即用的框架，将恢复尺度视为空间变化且阶段相关的连续变量。GraLoD重用原生编码器层级，将其多尺度特征对齐到共享的LOD表示空间，并在每个解码器阶段预测一个阶段条件的LOD场。每个空间位置随后仅连续查询两个相邻的表示层级，使有效恢复尺度能够适应局部图像内容和重建进度。为防止退化或任意的尺度选择，我们进一步引入了最小充分足迹校准（MSFC）和结构感知正则化（SAR），以鼓励恢复有效且空间连贯的LOD分配。GraLoD可直接集成到现有恢复骨干网络中，无需重新设计其基本特征处理模块。大量实验表明，在任务特定和全能恢复中均取得了一致的改进。
英文摘要：
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.
