Curvature Fields from Shading Fields

Published: 29 Nov 2023, Last Modified: 29 Nov 2023NeurReps 2023 PosterEveryoneRevisionsBibTeX
Submission Track: Proceedings
Keywords: shape perception, neural distance field, shape from shading, low-level vision
Abstract: We re-examine the estimation of 3D shape from images that are caused by shading of diffuse Lambertian surfaces. We propose a neural model that is motivated by the well-documented perceptual effect in which shape is perceived from shading without a precise perception of lighting. Our model operates independently in each receptive field and produces a scalar statistic of surface curvature for that field. The model’s architecture builds on previous mathematical analyses of lighting-invariant shape constraints, and it leverages geometric structure to provide equivariance under image rotations and translations. Applying our model in parallel across a dense set of receptive fields produces a curvature field that we show is quite stable under changes to a surface’s albedo pattern (texture) and also to changes in lighting, even when lighting varies spatially across the surface.
Submission Number: 67