GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation 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_ | 1866910371196960768 |
|---|---|
| author | Fu, Xiao Yin, Wei Hu, Mu Wang, Kaixuan Ma, Yuexin Tan, Ping Shen, Shaojie Lin, Dahua Long, Xiaoxiao |
| author_facet | Fu, Xiao Yin, Wei Hu, Mu Wang, Kaixuan Ma, Yuexin Tan, Ping Shen, Shaojie Lin, Dahua Long, Xiaoxiao |
| contents | We introduce GeoWizard, a new generative foundation model designed for estimating geometric attributes, e.g., depth and normals, from single images. While significant research has already been conducted in this area, the progress has been substantially limited by the low diversity and poor quality of publicly available datasets. As a result, the prior works either are constrained to limited scenarios or suffer from the inability to capture geometric details. In this paper, we demonstrate that generative models, as opposed to traditional discriminative models (e.g., CNNs and Transformers), can effectively address the inherently ill-posed problem. We further show that leveraging diffusion priors can markedly improve generalization, detail preservation, and efficiency in resource usage. Specifically, we extend the original stable diffusion model to jointly predict depth and normal, allowing mutual information exchange and high consistency between the two representations. More importantly, we propose a simple yet effective strategy to segregate the complex data distribution of various scenes into distinct sub-distributions. This strategy enables our model to recognize different scene layouts, capturing 3D geometry with remarkable fidelity. GeoWizard sets new benchmarks for zero-shot depth and normal prediction, significantly enhancing many downstream applications such as 3D reconstruction, 2D content creation, and novel viewpoint synthesis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12013 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image Fu, Xiao Yin, Wei Hu, Mu Wang, Kaixuan Ma, Yuexin Tan, Ping Shen, Shaojie Lin, Dahua Long, Xiaoxiao Computer Vision and Pattern Recognition We introduce GeoWizard, a new generative foundation model designed for estimating geometric attributes, e.g., depth and normals, from single images. While significant research has already been conducted in this area, the progress has been substantially limited by the low diversity and poor quality of publicly available datasets. As a result, the prior works either are constrained to limited scenarios or suffer from the inability to capture geometric details. In this paper, we demonstrate that generative models, as opposed to traditional discriminative models (e.g., CNNs and Transformers), can effectively address the inherently ill-posed problem. We further show that leveraging diffusion priors can markedly improve generalization, detail preservation, and efficiency in resource usage. Specifically, we extend the original stable diffusion model to jointly predict depth and normal, allowing mutual information exchange and high consistency between the two representations. More importantly, we propose a simple yet effective strategy to segregate the complex data distribution of various scenes into distinct sub-distributions. This strategy enables our model to recognize different scene layouts, capturing 3D geometry with remarkable fidelity. GeoWizard sets new benchmarks for zero-shot depth and normal prediction, significantly enhancing many downstream applications such as 3D reconstruction, 2D content creation, and novel viewpoint synthesis. |
| title | GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.12013 |