Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929561751519232 |
|---|---|
| author | Wu, Kailu Liu, Fangfu Cai, Zhihan Yan, Runjie Wang, Hanyang Hu, Yating Duan, Yueqi Ma, Kaisheng |
| author_facet | Wu, Kailu Liu, Fangfu Cai, Zhihan Yan, Runjie Wang, Hanyang Hu, Yating Duan, Yueqi Ma, Kaisheng |
| contents | In this work, we introduce Unique3D, a novel image-to-3D framework for efficiently generating high-quality 3D meshes from single-view images, featuring state-of-the-art generation fidelity and strong generalizability. Previous methods based on Score Distillation Sampling (SDS) can produce diversified 3D results by distilling 3D knowledge from large 2D diffusion models, but they usually suffer from long per-case optimization time with inconsistent issues. Recent works address the problem and generate better 3D results either by finetuning a multi-view diffusion model or training a fast feed-forward model. However, they still lack intricate textures and complex geometries due to inconsistency and limited generated resolution. To simultaneously achieve high fidelity, consistency, and efficiency in single image-to-3D, we propose a novel framework Unique3D that includes a multi-view diffusion model with a corresponding normal diffusion model to generate multi-view images with their normal maps, a multi-level upscale process to progressively improve the resolution of generated orthographic multi-views, as well as an instant and consistent mesh reconstruction algorithm called ISOMER, which fully integrates the color and geometric priors into mesh results. Extensive experiments demonstrate that our Unique3D significantly outperforms other image-to-3D baselines in terms of geometric and textural details. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_20343 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image Wu, Kailu Liu, Fangfu Cai, Zhihan Yan, Runjie Wang, Hanyang Hu, Yating Duan, Yueqi Ma, Kaisheng Computer Vision and Pattern Recognition Graphics Machine Learning I.2.10 In this work, we introduce Unique3D, a novel image-to-3D framework for efficiently generating high-quality 3D meshes from single-view images, featuring state-of-the-art generation fidelity and strong generalizability. Previous methods based on Score Distillation Sampling (SDS) can produce diversified 3D results by distilling 3D knowledge from large 2D diffusion models, but they usually suffer from long per-case optimization time with inconsistent issues. Recent works address the problem and generate better 3D results either by finetuning a multi-view diffusion model or training a fast feed-forward model. However, they still lack intricate textures and complex geometries due to inconsistency and limited generated resolution. To simultaneously achieve high fidelity, consistency, and efficiency in single image-to-3D, we propose a novel framework Unique3D that includes a multi-view diffusion model with a corresponding normal diffusion model to generate multi-view images with their normal maps, a multi-level upscale process to progressively improve the resolution of generated orthographic multi-views, as well as an instant and consistent mesh reconstruction algorithm called ISOMER, which fully integrates the color and geometric priors into mesh results. Extensive experiments demonstrate that our Unique3D significantly outperforms other image-to-3D baselines in terms of geometric and textural details. |
| title | Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image |
| topic | Computer Vision and Pattern Recognition Graphics Machine Learning I.2.10 |
| url | https://arxiv.org/abs/2405.20343 |