Geodesic-HOF: 3D Reconstruction Without Cutting Corners
This addresses a specific challenge in computer vision for 3D reconstruction, but it is incremental as it builds on existing methods by adding geodesic information.
The paper tackles the problem of single-view 3D object reconstruction, where high curvature regions often lead to poor reconstructions, and proposes a method that learns a geodesic embedding to improve surface estimation, resulting in better performance for surface normals and surface generation compared to point cloud reconstructions alone.
Single-view 3D object reconstruction is a challenging fundamental problem in computer vision, largely due to the morphological diversity of objects in the natural world. In particular, high curvature regions are not always captured effectively by methods trained using only set-based loss functions, resulting in reconstructions short-circuiting the surface or cutting corners. In particular, high curvature regions are not always captured effectively by methods trained using only set-based loss functions, resulting in reconstructions short-circuiting the surface or cutting corners. To address this issue, we propose learning an image-conditioned mapping function from a canonical sampling domain to a high dimensional space where the Euclidean distance is equal to the geodesic distance on the object. The first three dimensions of a mapped sample correspond to its 3D coordinates. The additional lifted components contain information about the underlying geodesic structure. Our results show that taking advantage of these learned lifted coordinates yields better performance for estimating surface normals and generating surfaces than using point cloud reconstructions alone. Further, we find that this learned geodesic embedding space provides useful information for applications such as unsupervised object decomposition.