Geometry-Aware Network for Non-Rigid Shape Prediction from a Single View
This addresses the challenge of non-rigid shape prediction for applications like computer vision and robotics, offering a more robust and efficient method compared to prior work.
The paper tackles the problem of predicting 3D shapes of deformable surfaces from a single view without needing a pre-registered template, achieving consistent improvements over state-of-the-art solutions with significantly lower computational time.
We propose a method for predicting the 3D shape of a deformable surface from a single view. By contrast with previous approaches, we do not need a pre-registered template of the surface, and our method is robust to the lack of texture and partial occlusions. At the core of our approach is a {\it geometry-aware} deep architecture that tackles the problem as usually done in analytic solutions: first perform 2D detection of the mesh and then estimate a 3D shape that is geometrically consistent with the image. We train this architecture in an end-to-end manner using a large dataset of synthetic renderings of shapes under different levels of deformation, material properties, textures and lighting conditions. We evaluate our approach on a test split of this dataset and available real benchmarks, consistently improving state-of-the-art solutions with a significantly lower computational time.