Saved in:
Bibliographic Details
Main Authors: Heo, Hwan, Kim, Jangyeong, Lee, Seongyeong, Wi, Jeong A, Choi, Junyoung, Ahn, Sangjun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.09433
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909457749901312
author Heo, Hwan
Kim, Jangyeong
Lee, Seongyeong
Wi, Jeong A
Choi, Junyoung
Ahn, Sangjun
author_facet Heo, Hwan
Kim, Jangyeong
Lee, Seongyeong
Wi, Jeong A
Choi, Junyoung
Ahn, Sangjun
contents The synthesis of high-quality 3D assets from textual or visual inputs has become a central objective in modern generative modeling. Despite the proliferation of 3D generation algorithms, they frequently grapple with challenges such as multi-view inconsistency, slow generation times, low fidelity, and surface reconstruction problems. While some studies have addressed some of these issues, a comprehensive solution remains elusive. In this paper, we introduce \textbf{CaPa}, a carve-and-paint framework that generates high-fidelity 3D assets efficiently. CaPa employs a two-stage process, decoupling geometry generation from texture synthesis. Initially, a 3D latent diffusion model generates geometry guided by multi-view inputs, ensuring structural consistency across perspectives. Subsequently, leveraging a novel, model-agnostic Spatially Decoupled Attention, the framework synthesizes high-resolution textures (up to 4K) for a given geometry. Furthermore, we propose a 3D-aware occlusion inpainting algorithm that fills untextured regions, resulting in cohesive results across the entire model. This pipeline generates high-quality 3D assets in less than 30 seconds, providing ready-to-use outputs for commercial applications. Experimental results demonstrate that CaPa excels in both texture fidelity and geometric stability, establishing a new standard for practical, scalable 3D asset generation.
format Preprint
id arxiv_https___arxiv_org_abs_2501_09433
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CaPa: Carve-n-Paint Synthesis for Efficient 4K Textured Mesh Generation
Heo, Hwan
Kim, Jangyeong
Lee, Seongyeong
Wi, Jeong A
Choi, Junyoung
Ahn, Sangjun
Computer Vision and Pattern Recognition
Graphics
The synthesis of high-quality 3D assets from textual or visual inputs has become a central objective in modern generative modeling. Despite the proliferation of 3D generation algorithms, they frequently grapple with challenges such as multi-view inconsistency, slow generation times, low fidelity, and surface reconstruction problems. While some studies have addressed some of these issues, a comprehensive solution remains elusive. In this paper, we introduce \textbf{CaPa}, a carve-and-paint framework that generates high-fidelity 3D assets efficiently. CaPa employs a two-stage process, decoupling geometry generation from texture synthesis. Initially, a 3D latent diffusion model generates geometry guided by multi-view inputs, ensuring structural consistency across perspectives. Subsequently, leveraging a novel, model-agnostic Spatially Decoupled Attention, the framework synthesizes high-resolution textures (up to 4K) for a given geometry. Furthermore, we propose a 3D-aware occlusion inpainting algorithm that fills untextured regions, resulting in cohesive results across the entire model. This pipeline generates high-quality 3D assets in less than 30 seconds, providing ready-to-use outputs for commercial applications. Experimental results demonstrate that CaPa excels in both texture fidelity and geometric stability, establishing a new standard for practical, scalable 3D asset generation.
title CaPa: Carve-n-Paint Synthesis for Efficient 4K Textured Mesh Generation
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2501.09433