Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.05054 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913226151690240 |
|---|---|
| author | Tang, Jiaxiang Chen, Zhaoxi Chen, Xiaokang Wang, Tengfei Zeng, Gang Liu, Ziwei |
| author_facet | Tang, Jiaxiang Chen, Zhaoxi Chen, Xiaokang Wang, Tengfei Zeng, Gang Liu, Ziwei |
| contents | 3D content creation has achieved significant progress in terms of both quality and speed. Although current feed-forward models can produce 3D objects in seconds, their resolution is constrained by the intensive computation required during training. In this paper, we introduce Large Multi-View Gaussian Model (LGM), a novel framework designed to generate high-resolution 3D models from text prompts or single-view images. Our key insights are two-fold: 1) 3D Representation: We propose multi-view Gaussian features as an efficient yet powerful representation, which can then be fused together for differentiable rendering. 2) 3D Backbone: We present an asymmetric U-Net as a high-throughput backbone operating on multi-view images, which can be produced from text or single-view image input by leveraging multi-view diffusion models. Extensive experiments demonstrate the high fidelity and efficiency of our approach. Notably, we maintain the fast speed to generate 3D objects within 5 seconds while boosting the training resolution to 512, thereby achieving high-resolution 3D content generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05054 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation Tang, Jiaxiang Chen, Zhaoxi Chen, Xiaokang Wang, Tengfei Zeng, Gang Liu, Ziwei Computer Vision and Pattern Recognition 3D content creation has achieved significant progress in terms of both quality and speed. Although current feed-forward models can produce 3D objects in seconds, their resolution is constrained by the intensive computation required during training. In this paper, we introduce Large Multi-View Gaussian Model (LGM), a novel framework designed to generate high-resolution 3D models from text prompts or single-view images. Our key insights are two-fold: 1) 3D Representation: We propose multi-view Gaussian features as an efficient yet powerful representation, which can then be fused together for differentiable rendering. 2) 3D Backbone: We present an asymmetric U-Net as a high-throughput backbone operating on multi-view images, which can be produced from text or single-view image input by leveraging multi-view diffusion models. Extensive experiments demonstrate the high fidelity and efficiency of our approach. Notably, we maintain the fast speed to generate 3D objects within 5 seconds while boosting the training resolution to 512, thereby achieving high-resolution 3D content generation. |
| title | LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.05054 |