Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908291443982336 |
|---|---|
| author | Ye, Chongjie Wu, Yushuang Lu, Ziteng Chang, Jiahao Guo, Xiaoyang Zhou, Jiaqing Zhao, Hao Han, Xiaoguang |
| author_facet | Ye, Chongjie Wu, Yushuang Lu, Ziteng Chang, Jiahao Guo, Xiaoyang Zhou, Jiaqing Zhao, Hao Han, Xiaoguang |
| contents | With the growing demand for high-fidelity 3D models from 2D images, existing methods still face significant challenges in accurately reproducing fine-grained geometric details due to limitations in domain gaps and inherent ambiguities in RGB images. To address these issues, we propose Hi3DGen, a novel framework for generating high-fidelity 3D geometry from images via normal bridging. Hi3DGen consists of three key components: (1) an image-to-normal estimator that decouples the low-high frequency image pattern with noise injection and dual-stream training to achieve generalizable, stable, and sharp estimation; (2) a normal-to-geometry learning approach that uses normal-regularized latent diffusion learning to enhance 3D geometry generation fidelity; and (3) a 3D data synthesis pipeline that constructs a high-quality dataset to support training. Extensive experiments demonstrate the effectiveness and superiority of our framework in generating rich geometric details, outperforming state-of-the-art methods in terms of fidelity. Our work provides a new direction for high-fidelity 3D geometry generation from images by leveraging normal maps as an intermediate representation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22236 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging Ye, Chongjie Wu, Yushuang Lu, Ziteng Chang, Jiahao Guo, Xiaoyang Zhou, Jiaqing Zhao, Hao Han, Xiaoguang Graphics Computer Vision and Pattern Recognition With the growing demand for high-fidelity 3D models from 2D images, existing methods still face significant challenges in accurately reproducing fine-grained geometric details due to limitations in domain gaps and inherent ambiguities in RGB images. To address these issues, we propose Hi3DGen, a novel framework for generating high-fidelity 3D geometry from images via normal bridging. Hi3DGen consists of three key components: (1) an image-to-normal estimator that decouples the low-high frequency image pattern with noise injection and dual-stream training to achieve generalizable, stable, and sharp estimation; (2) a normal-to-geometry learning approach that uses normal-regularized latent diffusion learning to enhance 3D geometry generation fidelity; and (3) a 3D data synthesis pipeline that constructs a high-quality dataset to support training. Extensive experiments demonstrate the effectiveness and superiority of our framework in generating rich geometric details, outperforming state-of-the-art methods in terms of fidelity. Our work provides a new direction for high-fidelity 3D geometry generation from images by leveraging normal maps as an intermediate representation. |
| title | Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.22236 |