Sparse GPU Voxelization for 3D Surface Reconstruction

摘要

Processes and systems described herein enable a computing device to perform voxel-based three-dimensional (3D) reconstruction modeling using parallel graphics hardware. The computing device may generate an initial low resolution voxel list. The voxels of the voxel list may be represented as index triples corresponding to the 3D spatial location of a cell within a voxel grid (e.g., {ix, iy, iz}). Based on information of input images associated with an object, the computing device may remove certain voxels that do not intersect with a surface of the object. The remaining voxels may be subdivided one or more times into a certain number of sub-voxels in parallel to generate a new voxel list. The newly generated voxel list may be tested again to determine voxels that do not intersect with the object surface. This process may repeat in part. The output voxels may be rendered as projected images.

主权项

1. A computer-implemented method for three-dimensional (3D) model reconstruction, the method comprising:
receiving input images that include multiple two-dimensional (2D) images of an object from various perspectives; generating a list of voxels that reconstruct a 3D model of the object based at least in part on the input images of the object, the list of voxels including multiple voxels; assigning individual voxels of the multiple voxels to a thread identifier (ID) associated with a graphics processing unit (GPU); removing one or more voxels from the list of voxels to generate output voxels that exclude the one or more voxels, the one or more voxels removed after the one or more voxels are identified as not intersecting with a surface of the object based on analysis of the input images; and rendering the 3D model using the output voxels.