NeuralODF: Learning Omnidirectional Distance Fields for 3D Shape Representation
This addresses the need for flexible 3D shape representation in visual computing, allowing modeling of open surfaces like garments, which is incremental as it builds on existing distance field methods.
The paper tackles the problem of representing 3D geometry by proposing Omnidirectional Distance Fields (ODFs), a new representation that encodes depth from any position and direction, enabling easy transformation to and from common forms like meshes or point clouds, and demonstrates that NeuralODF can learn high-quality shapes, overfitting to single objects and generalizing on shape categories.
In visual computing, 3D geometry is represented in many different forms including meshes, point clouds, voxel grids, level sets, and depth images. Each representation is suited for different tasks thus making the transformation of one representation into another (forward map) an important and common problem. We propose Omnidirectional Distance Fields (ODFs), a new 3D shape representation that encodes geometry by storing the depth to the object's surface from any 3D position in any viewing direction. Since rays are the fundamental unit of an ODF, it can be used to easily transform to and from common 3D representations like meshes or point clouds. Different from level set methods that are limited to representing closed surfaces, ODFs are unsigned and can thus model open surfaces (e.g., garments). We demonstrate that ODFs can be effectively learned with a neural network (NeuralODF) despite the inherent discontinuities at occlusion boundaries. We also introduce efficient forward mapping algorithms for transforming ODFs to and from common 3D representations. Specifically, we introduce an efficient Jumping Cubes algorithm for generating meshes from ODFs. Experiments demonstrate that NeuralODF can learn to capture high-quality shape by overfitting to a single object, and also learn to generalize on common shape categories.