MatAtlas: Text-driven Consistent Geometry Texturing and Material Assignment

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ceylan, Duygu, Deschaintre, Valentin, Groueix, Thibault, Martin, Rosalie, Huang, Chun-Hao, Rouffet, Romain, Kim, Vladimir, Lassagne, Gaëtan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910415498248192
author Ceylan, Duygu
Deschaintre, Valentin
Groueix, Thibault
Martin, Rosalie
Huang, Chun-Hao
Rouffet, Romain
Kim, Vladimir
Lassagne, Gaëtan
author_facet Ceylan, Duygu
Deschaintre, Valentin
Groueix, Thibault
Martin, Rosalie
Huang, Chun-Hao
Rouffet, Romain
Kim, Vladimir
Lassagne, Gaëtan
contents We present MatAtlas, a method for consistent text-guided 3D model texturing. Following recent progress we leverage a large scale text-to-image generation model (e.g., Stable Diffusion) as a prior to texture a 3D model. We carefully design an RGB texturing pipeline that leverages a grid pattern diffusion, driven by depth and edges. By proposing a multi-step texture refinement process, we significantly improve the quality and 3D consistency of the texturing output. To further address the problem of baked-in lighting, we move beyond RGB colors and pursue assigning parametric materials to the assets. Given the high-quality initial RGB texture, we propose a novel material retrieval method capitalized on Large Language Models (LLM), enabling editabiliy and relightability. We evaluate our method on a wide variety of geometries and show that our method significantly outperform prior arts. We also analyze the role of each component through a detailed ablation study.
format Preprint
id arxiv_https___arxiv_org_abs_2404_02899
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MatAtlas: Text-driven Consistent Geometry Texturing and Material Assignment
Ceylan, Duygu
Deschaintre, Valentin
Groueix, Thibault
Martin, Rosalie
Huang, Chun-Hao
Rouffet, Romain
Kim, Vladimir
Lassagne, Gaëtan
Computer Vision and Pattern Recognition
Graphics
We present MatAtlas, a method for consistent text-guided 3D model texturing. Following recent progress we leverage a large scale text-to-image generation model (e.g., Stable Diffusion) as a prior to texture a 3D model. We carefully design an RGB texturing pipeline that leverages a grid pattern diffusion, driven by depth and edges. By proposing a multi-step texture refinement process, we significantly improve the quality and 3D consistency of the texturing output. To further address the problem of baked-in lighting, we move beyond RGB colors and pursue assigning parametric materials to the assets. Given the high-quality initial RGB texture, we propose a novel material retrieval method capitalized on Large Language Models (LLM), enabling editabiliy and relightability. We evaluate our method on a wide variety of geometries and show that our method significantly outperform prior arts. We also analyze the role of each component through a detailed ablation study.
title MatAtlas: Text-driven Consistent Geometry Texturing and Material Assignment
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2404.02899