Deformable Surface Reconstruction via Riemannian Metric Preservation
This addresses the inverse problem of object pose estimation in computer vision, which is incremental as it builds on known deformation priors.
The paper tackles the problem of reconstructing deformable surfaces from monocular image sequences by incorporating a Riemannian metric preservation prior, achieving state-of-the-art performance without offline training.
Estimating the pose of an object from a monocular image is an inverse problem fundamental in computer vision. The ill-posed nature of this problem requires incorporating deformation priors to solve it. In practice, many materials do not perceptibly shrink or extend when manipulated, constituting a powerful and well-known prior. Mathematically, this translates to the preservation of the Riemannian metric. Neural networks offer the perfect playground to solve the surface reconstruction problem as they can approximate surfaces with arbitrary precision and allow the computation of differential geometry quantities. This paper presents an approach to inferring continuous deformable surfaces from a sequence of images, which is benchmarked against several techniques and obtains state-of-the-art performance without the need for offline training.