Abstract
The representation of voxel colors has become crucial because voxelized 3D data are used in a variety of applications. In particular, texture atlases are widely used for representing voxel colors. The texture atlas is typically utilized for encoding voxel colors using image/video encoders, so it is important to design a texture atlas while maintaining the connectivity between voxels. In this paper, we present a texture atlas based on a surface scanning scheme. To this end, we represent a 3D object as slices, and texture strips are obtained by scanning voxels along the surface for each slice. The texture strips represent the voxel colors while preserving the connectivity of the voxels. Besides, because the texture strips are highly correlated, we construct a texture atlas by aligning texture strips. We also propose a partitioning method for a 3D object to solve the self-occlusion problem that occurs in the alignment process. As an application of the proposed texture atlases, we utilize it for encoding voxel colors and propose encoding strategies. Experimental results indicate that the proposed texture atlases outperform the previous methods. To the best of our knowledge, this is the first attempt to use a surface scanning scheme for a texture atlas.
Highlights
Voxel-based data have been used in computer vision research fields
3D point clouds acquired by depth sensors, Lidar, and stereo cameras are commonly converted to voxels because they are more convenient to manipulate than other 3D data representations
OVERVIEW The framework of the surface scanning-based texture atlases generator (SSTAG) is shown in figure 2 and consists of the following steps: 1) Partitioning 3D object: As we briefly introduced in section I, a voxelized 3D object is partitioned into a set of voxel clusters; we prevent the self-occlusion problem
Summary
Voxel-based data have been used in computer vision research fields. For instance, 3D point clouds acquired by depth sensors, Lidar, and stereo cameras are commonly converted to voxels because they are more convenient to manipulate than other 3D data representations. Compared to the previous works, the proposed method makes the following contributions: 1) To address the problems of the previous works, we propose a surface scanning-based texture atlas for voxelized surface data To this end, a voxelized 3D object is represented as a set of slices, and a texture strip is generated using a boundary tracing algorithm for each slice. OVERVIEW The framework of the surface scanning-based texture atlases generator (SSTAG) is shown in figure 2 and consists of the following steps: 1) Partitioning 3D object: As we briefly introduced, a voxelized 3D object is partitioned into a set of voxel clusters; we prevent the self-occlusion problem. The intermediate method efficiently maintains the connectivity of the voxels but has problems, such as self-occlusion and 2D space quantization To solve those problems while preserving the connectivity of the voxels, we proposed surface scanningbased texture atlases. Our texture atlas maintains the connectivity of voxels and solves the problems of previous works
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
