TwinTex: Geometry-Aware Texture Generation for Abstracted 3D Architectural Models
ACM Transactions on Graphics · 05.12.2023 · 42 (6) · 1-14
DOI: 10.1145/3618328 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 05.12.2023. Verfasst von Weidan Xiong und 6 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 77 Literaturangaben. Gefördert von: DEGP Innovation Team, NSFC, Shenzhen Science and Technology Program.
Abstract (Originalsprache)
Coarse architectural models are often generated at scales ranging from individual buildings to scenes for downstream applications such as Digital Twin City, Metaverse, LODs, etc. Such piece-wise planar models can be abstracted as twins from 3D dense reconstructions. However, these models typically lack realistic texture relative to the real building or scene, making them unsuitable for vivid display or direct reference. In this paper, we present TwinTex , the first automatic texture mapping framework to generate a photorealistic texture for a piece-wise planar proxy. Our method addresses most challenges occurring in such twin texture generation. Specifically, for each primitive plane, we first select a small set of photos with greedy heuristics considering photometric quality, perspective quality and facade texture completeness. Then, different levels of line features (LoLs) are extracted from the set of selected photos to generate guidance for later steps. With LoLs, we employ optimization algorithms to align texture with geometry from local to global. Finally, we fine-tune a diffusion model with a multi-mask initialization component and a new dataset to inpaint the missing region. Experimental results on many buildings, indoor scenes and man-made objects of varying complexity demonstrate the generalization ability of our algorithm. Our approach surpasses state-of-the-art texture mapping methods in terms of high-fidelity quality and reaches a human-expert production level with much less effort.
Förderung
- DEGP Innovation Team
- NSFC
- Shenzhen Science and Technology Program
Zitieren
APA
Xiong, W., Zhang, H., Peng, B., Hu, Z., Wu, Y., Guo, J., & Huang, H. (2023). TwinTex: Geometry-Aware Texture Generation for Abstracted 3D Architectural Models. ACM Transactions on Graphics, 42(6), 1-14. https://doi.org/10.1145/3618328
Vancouver
Xiong W, Zhang H, Peng B, Hu Z, Wu Y, Guo J, et al. TwinTex: Geometry-Aware Texture Generation for Abstracted 3D Architectural Models. ACM Transactions on Graphics. 2023;42(6):1-14. doi:10.1145/3618328
BibTeX
@article{Xiong2023,
author = {Xiong, Weidan and Zhang, Hongqian and Peng, Botao and Hu, Ziyu and Wu, Yongli and Guo, Jianwei and Huang, Hui},
title = {TwinTex: Geometry-Aware Texture Generation for Abstracted 3D Architectural Models},
journal = {ACM Transactions on Graphics},
year = {2023},
volume = {42},
number = {6},
pages = {1--14},
doi = {10.1145/3618328}
}
EUVIMED