From Shading to Local Shape

Abstract

We develop a framework for extracting a concise representation of the shape information available from diffuse shading in a small image patch. This produces a mid-level scene descriptor, comprised of local shape distributions that are inferred separately at every image patch across multiple scales. The framework is based on a quadratic representation of local shape that, in the absence of noise, has guarantees on recovering accurate local shape and lighting. And when noise is present, the inferred local shape distributions provide useful shape information without over-committing to any particular image explanation. These local shape distributions naturally encode the fact that some smooth diffuse regions are more informative than others, and they enable efficient and robust reconstruction of object-scale shape. Experimental results show that this approach to surface reconstruction compares well against the state-of-art on both synthetic images and captured photographs.

References in corpus (1)

• Characterizing Ambiguity in Light Source Invariant Shape from Shading

Cited by in corpus (13)

• Polarimetric Multi-View Inverse Rendering
• A CNN Based Approach for the Point-Light Photometric Stereo Problem
• Learning to Reconstruct Texture-less Deformable Surfaces from a Single View
• Deep Shape from Polarization
• 3D Fourier ghost imaging via semi-calibrated photometric stereo
• Single-image RGB Photometric Stereo With Spatially-varying Albedo
• What's In A Patch, I: Tensors, Differential Geometry and Statistical Shading Analysis
• Shape from Shading through Shape Evolution
• Tensors, Differential Geometry and Statistical Shading Analysis
• Polarimetric Multi-View Inverse Rendering
• Solving Uncalibrated Photometric Stereo Using Fewer Images by Jointly Optimizing Low-rank Matrix Completion and Integrability
• Active Lighting Recurrence by Parallel Lighting Analogy for Fine-Grained Change Detection
• Low-level Vision by Consensus in a Spatial Hierarchy of Regions