TwinTex: Geometry-aware Texture Generation for Abstracted 3D Architectural Models

TL;DR

TwinTex is an innovative framework that automatically generates photo-realistic textures for 3D architectural models, enhancing visual fidelity for applications like digital twins and the Metaverse.

Contribution

It introduces the first automatic texture mapping method that combines photo selection, line feature guidance, optimization, and diffusion-based inpainting for piece-wise planar models.

Findings

Outperforms state-of-the-art texture mapping methods in quality.

Achieves human-expert level results with less effort.

Demonstrates generalization across various building and scene types.

Abstract

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. Project page: https://vcc.tech/research/2023/TwinTex.