Tetrahedron Splatting for 3D Generation
Authors: Chun Gu, Zeyu Yang, Zijie Pan, Xiatian Zhu, Li Zhang
NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments show that our Te T-Splatting strikes a superior tradeoff among convergence speed, render efficiency, and mesh quality as compared to previous alternatives under varying 3D generation settings. |
| Researcher Affiliation | Academia | Chun Gu1 Zeyu Yang1 Zijie Pan1 Xiatian Zhu2 Li Zhang1 1School of Data Science, Fudan University 2University of Surrey |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | https://fudan-zvg.github.io/tet-splatting |
| Open Datasets | Yes | To validate the capability of Te T-Splatting for 3D generation, we employ two types of diffusion priors: the vanilla RGB-based diffusion priors and the rich diffusion priors proposed in Rich Dreamer [34]... We adapt the diffusion priors of all methods to Stable Zero-1-to-3 [20] for a fair comparison in the image-to-3D task... we calculate our scores using an alternative set of prompts (see Appendix B for details). |
| Dataset Splits | No | The paper does not explicitly provide training/validation/test dataset splits with specific percentages or counts. |
| Hardware Specification | Yes | Note that all experiments are conducted on one NVIDIA RTX A6000 GPU. |
| Software Dependencies | No | The paper mentions 'Stable Diffusion 2.1 base' but does not provide version numbers for other key software components like 'threestudio codebase' or 'Rich Dreamer codebase'. |
| Experiment Setup | Yes | For the schedule of the s value in Eq. 1, we set sratio = 5 and sstart = 20... Additionally, we set both λeik and λnc to 1000... The tetrahedral grid resolution is set to 128, and the batch size is set to 1... The geometry is optimized for 3,000 iterations and the texture for another 1,000 iterations... We set the loss weights λrgb and λmask to 10,000 and 1,000, respectively. Also, we decrease λeik and sratio to 100 and 2, respectively... The tetrahedral grid resolution is set to 256 and the batch size is set to 4 for two stages. We optimize the geometry for 3,000 steps, with the first 1,000 steps using latent code, followed by an additional 2,000 steps for texture optimization. While Rich Dreamer reports significantly increased stability at a rendering resolution of 1024, we achieve stable results at a lower resolution of 512. Therefore, we set our rendering resolution to 512. |