Texture-aware Intrinsic Image Decomposition with Model- and Learning-based Priors
This work addresses the problem of recovering intrinsic reflectance and shading layers from single images for computer vision applications, representing an incremental improvement over prior methods.
The paper tackles the challenge of intrinsic image decomposition in complex scenes with spatially-varying lighting and rich textures, proposing a texture-guided regularization method that produces high-quality intrinsic images superior to existing approaches.
This paper aims to recover the intrinsic reflectance layer and shading layer given a single image. Though this intrinsic image decomposition problem has been studied for decades, it remains a significant challenge in cases of complex scenes, i.e. spatially-varying lighting effect and rich textures. In this paper, we propose a novel method for handling severe lighting and rich textures in intrinsic image decomposition, which enables to produce high-quality intrinsic images for real-world images. Specifically, we observe that previous learning-based methods tend to produce texture-less and over-smoothing intrinsic images, which can be used to infer the lighting and texture information given a RGB image. In this way, we design a texture-guided regularization term and formulate the decomposition problem into an optimization framework, to separate the material textures and lighting effect. We demonstrate that combining the novel texture-aware prior can produce superior results to existing approaches.