TwinTex: Geometry-aware Texture Generation for Abstracted 3D Architectural Models
文献类型：期刊论文
| 作者 | Xiong, Weidan4; Zhang, Hongqian4; Peng, Botao4; Hu, Ziyu3; Wu, Yongli3; Guo, Jianwei2 ; Huang, Hui1
|
| 刊名 | ACM TRANSACTIONS ON GRAPHICS
 |
| 出版日期 | 2023-12-01 |
| 卷号 | 42期号:6页码:14 |
| ISSN号 | 0730-0301 |
| 关键词 | Texture Mapping 3D Architectural Proxy View Selection Image Stitching Texture Optimization Diffusion Model |
| DOI | 10.1145/3618328 |
| 通讯作者 | Xiong, Weidan(xiongweidan@gmail.com) |
| 英文摘要 | 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 photo-realistic 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. |
| WOS关键词 | IMAGE ; RECONSTRUCTION |
| 资助项目 | NSFC[U21B2023] ; NSFC[U2001206] ; NSFC[U22B2034] ; NSFC[62172416] ; NSFC[62302313] ; DEGP Innovation Team[2022KCXTD025] ; Shenzhen Science and Technology Program[KQTD202108110900440 03] ; Shenzhen Science and Technology Program[RCJC20200714114435012] ; Shenzhen Science and Technology Program[JCYJ20210324120213036] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| 出版者 | ASSOC COMPUTING MACHINERY |
| WOS记录号 | WOS:001139790400055 |
| 资助机构 | NSFC ; DEGP Innovation Team ; Shenzhen Science and Technology Program |
| 源URL | [http://ir.ia.ac.cn/handle/173211/55449]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Xiong, Weidan |
| 作者单位 | 1.Shenzhen Univ, Coll Comp Sci & Software Engn, Shenzhen, Peoples R China 2.Chinese Acad Sci, Inst Automat, MAIS, Beijing, Peoples R China 3.Shenzhen Univ, Guangdong Artificial Intelligence & Digital Econ, Shenzhen, Peoples R China 4.Shenzhen Univ, Shenzhen, Peoples R China |
| 推荐引用方式 GB/T 7714 | Xiong, Weidan,Zhang, Hongqian,Peng, Botao,et al. TwinTex: Geometry-aware Texture Generation for Abstracted 3D Architectural Models[J]. ACM TRANSACTIONS ON GRAPHICS,2023,42(6):14. |
| APA | Xiong, Weidan.,Zhang, Hongqian.,Peng, Botao.,Hu, Ziyu.,Wu, Yongli.,...&Huang, Hui.(2023).TwinTex: Geometry-aware Texture Generation for Abstracted 3D Architectural Models.ACM TRANSACTIONS ON GRAPHICS,42(6),14. |
| MLA | Xiong, Weidan,et al."TwinTex: Geometry-aware Texture Generation for Abstracted 3D Architectural Models".ACM TRANSACTIONS ON GRAPHICS 42.6(2023):14. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。