Monocular Shape from Refraction

Refraction is a common physical phenomenon and has long been researched in computer vision. Objects imaged through a refractive object appear distorted in the image as a function of the shape of the interface between the media. This hinders many computer vision applications, but can be utilized for obtaining the geometry of the refractive interface. Previous approaches for refractive surface recovery largely relied on various priors or additional information like multiple images of the analyzed surface. In contrast, we claim that a simple energy function based on Snell's law enables the reconstruction of an arbitrary refractive surface geometry using just a single image and known background texture and geometry. In the case of a single point, Snell's law has two degrees of freedom, therefore to estimate a surface depth, we need additional information. We show that solving for an entire surface at once introduces implicit parameter-free spatial regularization and yields convincing results when an intelligent initial guess is provided. We demonstrate our approach through simulations and real-world experiments, where the reconstruction shows encouraging results in the single-frame monocular setting.



This is data and code for our work presented on BMVC'21 as an oral presentation. The paper itself presents an optimization approach to estimate a 3D surface structure from a single image with known background depth and texture.



owards Monocular Shape from Refraction.jpg

Antonin Sulc, Imari Sato, Bastian Goldluecke and Tali Treibitz. Towards Monocular Shape from Refraction, BMVC 2021. [PDF] [Supplementary Material].