解决低层视觉任务中图像亮度色彩不一致导致的训练偏差问题。
On the Global Photometric Alignment for Low-Level Vision
- 通过闭式仿射变换自动对齐每对图像的光照色彩，消除干扰
- 在6个任务16个数据集上均提升重建精度与泛化能力
- 无需额外参数，计算开销极小，适合各类低层视觉模型
监督式低层视觉模型依赖像素级损失函数与成对参考图像对比，但成对数据间存在光度不一致问题，例如不同图像对需要不同的全局亮度、颜色或白平衡映射。这种不一致源于任务内在的光度转换（如暗光增强）或非预期的采集差异（如去雨），均会引发优化病态。标准重建损失将过多梯度预算分配给冲突的光度目标，挤占内容恢复所需监督。本文分析表明，在最小二乘分解下，预测-目标残差中的光度分量与结构分量正交，且空间密集的光度分量主导梯度能量。基于此，提出光度对齐损失（PAL），通过闭式仿射颜色对齐机制，有效抑制无关光度差异，同时保留修复关键信息，仅需协方差统计和微小矩阵求逆，计算开销可忽略。在6项任务、16个数据集、16种架构上，PAL持续提升指标表现与泛化能力。实现见附录。
原文摘要 · Abstract (English)
Supervised low-level vision models rely on pixel-wise losses against paired references, yet paired training sets exhibit per-pair photometric inconsistency, say, different image pairs demand different global brightness, color, or white-balance mappings. This inconsistency enters through task-intrinsic photometric transfer (e.g., low-light enhancement) or unintended acquisition shifts (e.g., de-raining), and in either case causes an optimization pathology. Standard reconstruction losses allocate disproportionate gradient budget to conflicting per-pair photometric targets, crowding out content restoration. In this paper, we investigate this issue and prove that, under least-squares decomposition, the photometric and structural components of the prediction-target residual are orthogonal, and that the spatially dense photometric component dominates the gradient energy. Motivated by this analysis, we propose Photometric Alignment Loss (PAL). This flexible supervision objective discounts nuisance photometric discrepancy via closed-form affine color alignment while preserving restoration-relevant supervision, requiring only covariance statistics and tiny matrix inversion with negligible overhead. Across 6 tasks, 16 datasets, and 16 architectures, PAL consistently improves metrics and generalization. The implementation is in the appendix.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。