Result: DeepTex: Deep Learning-Based Texturing of Image-Based 3D Reconstructions
Title:
DeepTex: Deep Learning-Based Texturing of Image-Based 3D Reconstructions
Authors:
Publisher Information:
Fraunhofer-Gesellschaft, 2024.
Publication Year:
2024
Subject Terms:
Research Line: Computer vision (CV), LTA: Generation, capture, processing, and output of images and 3D models, Research Line: Machine learning (ML), Deep learning, LTA: Machine intelligence, algorithms, and data structures (incl. semantics), 3D Reconstruction, Texturing, Branche: Cultural and Creative Economy
Document Type:
Conference
Conference object
Language:
English
DOI:
10.24406/publica-4080
Accession Number:
edsair.doi...........3ab519ba0ff68fd7626c3a6c47b968f3
Database:
OpenAIRE
Further Information
Image-based 3D reconstruction is a commonly used technique for measuring the geometry and color of objects or scenes based on images. While the geometry reconstruction of state-of-the-art approaches is mostly robust against varying lighting conditions and outliers, these pose a significant challenge for calculating an accurate texture map. This work proposes a deep-learning based texturing approach called "DeepTex" that uses a custom learned blending method on top of a traditional mosaic-based texturing approach. The model was trained using a custom synthetic data generation workflow and showed a significantly increased accuracy when generating textures in the presence of outliers and non-uniform lighting.