GeoScaler: Geometry and Rendering-Aware Downsampling of 3D Mesh Textures

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pentapati, Sai Karthikey, Rai, Anshul, Ten, Arkady, Atluru, Chaitanya, Bovik, Alan
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916166998425600
author Pentapati, Sai Karthikey
Rai, Anshul
Ten, Arkady
Atluru, Chaitanya
Bovik, Alan
author_facet Pentapati, Sai Karthikey
Rai, Anshul
Ten, Arkady
Atluru, Chaitanya
Bovik, Alan
contents High-resolution texture maps are necessary for representing real-world objects accurately with 3D meshes. The large sizes of textures can bottleneck the real-time rendering of high-quality virtual 3D scenes on devices having low computational budgets and limited memory. Downsampling the texture maps directly addresses the issue, albeit at the cost of visual fidelity. Traditionally, downsampling of texture maps is performed using methods like bicubic interpolation and the Lanczos algorithm. These methods ignore the geometric layout of the mesh and its UV parametrization and also do not account for the rendering process used to obtain the final visualization that the users will experience. Towards filling these gaps, we introduce GeoScaler, which is a method of downsampling texture maps of 3D meshes while incorporating geometric cues, and by maximizing the visual fidelity of the rendered views of the textured meshes. We show that the textures generated by GeoScaler deliver significantly better quality rendered images compared to those generated by traditional downsampling methods
format Preprint
id arxiv_https___arxiv_org_abs_2311_16581
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle GeoScaler: Geometry and Rendering-Aware Downsampling of 3D Mesh Textures
Pentapati, Sai Karthikey
Rai, Anshul
Ten, Arkady
Atluru, Chaitanya
Bovik, Alan
Graphics
Computer Vision and Pattern Recognition
High-resolution texture maps are necessary for representing real-world objects accurately with 3D meshes. The large sizes of textures can bottleneck the real-time rendering of high-quality virtual 3D scenes on devices having low computational budgets and limited memory. Downsampling the texture maps directly addresses the issue, albeit at the cost of visual fidelity. Traditionally, downsampling of texture maps is performed using methods like bicubic interpolation and the Lanczos algorithm. These methods ignore the geometric layout of the mesh and its UV parametrization and also do not account for the rendering process used to obtain the final visualization that the users will experience. Towards filling these gaps, we introduce GeoScaler, which is a method of downsampling texture maps of 3D meshes while incorporating geometric cues, and by maximizing the visual fidelity of the rendered views of the textured meshes. We show that the textures generated by GeoScaler deliver significantly better quality rendered images compared to those generated by traditional downsampling methods
title GeoScaler: Geometry and Rendering-Aware Downsampling of 3D Mesh Textures
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.16581