Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Gradient-SDF: A Semi-Implicit Surface Representation for 3D Reconstruction

About

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.

Christiane Sommer, Lu Sang, David Schubert, Daniel Cremers• 2021

Related benchmarks

TaskDatasetResultRank
Visual SLAMTUM RGB-D fr1 desk
ATE RMSE (cm)0.056
21
Camera TrackingTUM RGB-D fr1 xyz
ATE RMSE (cm)2
4
Camera TrackingTUM RGB-D fr1 rpy
ATE RMSE (cm)4.9
4
Camera TrackingTUM RGB-D fr1 plant
ATE RMSE (cm)11.2
4
Camera TrackingTUM RGB-D fr1 teddy
ATE RMSE (cm)11.3
4
Camera TrackingTUM RGB-D fr3 household
ATE RMSE (cm)5.2
4
Visual SLAMTUM RGB-D fr1/desk2--
4
Showing 7 of 7 rows

Other info

Follow for update