论文标题
使用范式的固有图像分解
Intrinsic Image Decomposition using Paradigms
论文作者
论文摘要
固有图像分解是将图像映射到反照率的经典任务。 WHDR数据集允许通过将预测与人类判断进行比较（“较轻”，“与“更暗”）进行评估。最好的现代固有图像方法使用渲染模型和人类判断来学习从图像到反照率的地图。这对于实用方法很方便，但是无法解释没有几何，表面和照明模型以及渲染器可以学会恢复固有图像的视觉剂。 本文介绍了一种学习固有图像分解的方法，而无需看到whdr注释，渲染数据或地面真相数据。该方法依赖于范式 - 假反照率和假阴影场 - 以及一个新颖的平滑过程，可确保在真实图像上短尺度上的良好行为。长规模误差由平均控制控制。我们的方法与最新方法的竞争能力达到了WHDR分数，从而可以看到训练WHDR注释，渲染数据和地面真相数据。由于我们的方法是无监督的，因此我们可以计算WHDR分数的测试/火车方差的估计值；这些很大，在报告的WHDR中依靠微小差异是不安全的。
Intrinsic image decomposition is the classical task of mapping image to albedo. The WHDR dataset allows methods to be evaluated by comparing predictions to human judgements ("lighter", "same as", "darker"). The best modern intrinsic image methods learn a map from image to albedo using rendered models and human judgements. This is convenient for practical methods, but cannot explain how a visual agent without geometric, surface and illumination models and a renderer could learn to recover intrinsic images. This paper describes a method that learns intrinsic image decomposition without seeing WHDR annotations, rendered data, or ground truth data. The method relies on paradigms - fake albedos and fake shading fields - together with a novel smoothing procedure that ensures good behavior at short scales on real images. Long scale error is controlled by averaging. Our method achieves WHDR scores competitive with those of strong recent methods allowed to see training WHDR annotations, rendered data, and ground truth data. Because our method is unsupervised, we can compute estimates of the test/train variance of WHDR scores; these are quite large, and it is unsafe to rely small differences in reported WHDR.
