Deep Level Sets: Implicit Surface Representations for 3D Shape Inference
This addresses the problem of generating precise 3D surface meshes for computer vision and graphics applications, representing an incremental improvement over existing implicit surface methods.
The paper tackles the problem of inaccurate boundary classification in 3D surface representations, which leads to coarse outputs requiring post-processing, by proposing an end-to-end trainable model that predicts implicit surface representations using a novel geometric loss function, resulting in more accurate reconstructions compared to voxel-based methods.
Existing 3D surface representation approaches are unable to accurately classify pixels and their orientation lying on the boundary of an object. Thus resulting in coarse representations which usually require post-processing steps to extract 3D surface meshes. To overcome this limitation, we propose an end-to-end trainable model that directly predicts implicit surface representations of arbitrary topology by optimising a novel geometric loss function. Specifically, we propose to represent the output as an oriented level set of a continuous embedding function, and incorporate this in a deep end-to-end learning framework by introducing a variational shape inference formulation. We investigate the benefits of our approach on the task of 3D surface prediction and demonstrate its ability to produce a more accurate reconstruction compared to voxel-based representations. We further show that our model is flexible and can be applied to a variety of shape inference problems.