MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909290841767936 |
|---|---|
| author | Liu, Minghua Zeng, Chong Wei, Xinyue Shi, Ruoxi Chen, Linghao Xu, Chao Zhang, Mengqi Wang, Zhaoning Zhang, Xiaoshuai Liu, Isabella Wu, Hongzhi Su, Hao |
| author_facet | Liu, Minghua Zeng, Chong Wei, Xinyue Shi, Ruoxi Chen, Linghao Xu, Chao Zhang, Mengqi Wang, Zhaoning Zhang, Xiaoshuai Liu, Isabella Wu, Hongzhi Su, Hao |
| contents | Open-world 3D reconstruction models have recently garnered significant attention. However, without sufficient 3D inductive bias, existing methods typically entail expensive training costs and struggle to extract high-quality 3D meshes. In this work, we introduce MeshFormer, a sparse-view reconstruction model that explicitly leverages 3D native structure, input guidance, and training supervision. Specifically, instead of using a triplane representation, we store features in 3D sparse voxels and combine transformers with 3D convolutions to leverage an explicit 3D structure and projective bias. In addition to sparse-view RGB input, we require the network to take input and generate corresponding normal maps. The input normal maps can be predicted by 2D diffusion models, significantly aiding in the guidance and refinement of the geometry's learning. Moreover, by combining Signed Distance Function (SDF) supervision with surface rendering, we directly learn to generate high-quality meshes without the need for complex multi-stage training processes. By incorporating these explicit 3D biases, MeshFormer can be trained efficiently and deliver high-quality textured meshes with fine-grained geometric details. It can also be integrated with 2D diffusion models to enable fast single-image-to-3D and text-to-3D tasks. Project page: https://meshformer3d.github.io |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10198 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model Liu, Minghua Zeng, Chong Wei, Xinyue Shi, Ruoxi Chen, Linghao Xu, Chao Zhang, Mengqi Wang, Zhaoning Zhang, Xiaoshuai Liu, Isabella Wu, Hongzhi Su, Hao Computer Vision and Pattern Recognition Graphics Open-world 3D reconstruction models have recently garnered significant attention. However, without sufficient 3D inductive bias, existing methods typically entail expensive training costs and struggle to extract high-quality 3D meshes. In this work, we introduce MeshFormer, a sparse-view reconstruction model that explicitly leverages 3D native structure, input guidance, and training supervision. Specifically, instead of using a triplane representation, we store features in 3D sparse voxels and combine transformers with 3D convolutions to leverage an explicit 3D structure and projective bias. In addition to sparse-view RGB input, we require the network to take input and generate corresponding normal maps. The input normal maps can be predicted by 2D diffusion models, significantly aiding in the guidance and refinement of the geometry's learning. Moreover, by combining Signed Distance Function (SDF) supervision with surface rendering, we directly learn to generate high-quality meshes without the need for complex multi-stage training processes. By incorporating these explicit 3D biases, MeshFormer can be trained efficiently and deliver high-quality textured meshes with fine-grained geometric details. It can also be integrated with 2D diffusion models to enable fast single-image-to-3D and text-to-3D tasks. Project page: https://meshformer3d.github.io |
| title | MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2408.10198 |