Gradient-SDF: A Semi-Implicit Surface Representation for 3D Reconstruction
This work addresses 3D reconstruction for computer vision applications, offering an incremental improvement by integrating existing methods into a hybrid representation.
The paper tackles the problem of 3D reconstruction by introducing Gradient-SDF, a representation that combines implicit and explicit approaches to enhance geometry representation, resulting in significantly sharper reconstructions as confirmed by experiments.
We present Gradient-SDF, a novel representation for 3D geometry that combines the advantages of implict and explicit representations. By storing at every voxel both the signed distance field as well as its gradient vector field, we enhance the capability of implicit representations with approaches originally formulated for explicit surfaces. As concrete examples, we show that (1) the Gradient-SDF allows us to perform direct SDF tracking from depth images, using efficient storage schemes like hash maps, and that (2) the Gradient-SDF representation enables us to perform photometric bundle adjustment directly in a voxel representation (without transforming into a point cloud or mesh), naturally a fully implicit optimization of geometry and camera poses and easy geometry upsampling. Experimental results confirm that this leads to significantly sharper reconstructions. Since the overall SDF voxel structure is still respected, the proposed Gradient-SDF is equally suited for (GPU) parallelization as related approaches.