Ordinality of Visible-Thermal Image Intensities for Intrinsic Image Decomposition
This addresses the problem of decomposing images into shading and reflectance for computer vision applications, offering a scalable solution for real-world outdoor scenes where manual labeling is infeasible.
The paper tackles the challenge of intrinsic image decomposition without extensive ground-truth data by introducing a training-free method that uses visible and thermal image pairs to relate intensity ordinalities to shading and reflectance, achieving superior performance over recent learning-based models in quantitative and qualitative evaluations.
Decomposing an image into its intrinsic photometric factors--shading and reflectance--is a long-standing challenge due to the lack of extensive ground-truth data for real-world scenes. Recent methods rely on synthetic data or sparse annotations for limited indoor and even fewer outdoor scenes. We introduce a novel training-free approach for intrinsic image decomposition using only a pair of visible and thermal images. We leverage the principle that light not reflected from an opaque surface is absorbed and detected as heat by a thermal camera. This allows us to relate the ordinalities between visible and thermal image intensities to the ordinalities of shading and reflectance, which can densely self-supervise an optimizing neural network to recover shading and reflectance. We perform quantitative evaluations with known reflectance and shading under natural and artificial lighting, and qualitative experiments across diverse outdoor scenes. The results demonstrate superior performance over recent learning-based models and point toward a scalable path to curating real-world ordinal supervision, previously infeasible via manual labeling.