Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
(ICCV 2023) official repository for "Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation"
| Date | Stars |
|---|---|
| 2026-07-24 | 780 |
| 2026-07-25 | 780 |
| 2026-07-28 | 780 |
| 2026-07-30 | 780 |
| 2026-08-06 | 780 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# <p align="center"> <font color=#008000>Fantasia3D</font>: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation </p> ##### <p align="center"> [Rui Chen*](https://aruichen.github.io/), [Yongwei Chen*](https://cyw-3d.github.io/), [Ningxin Jiao](https://ningxinj.github.io/), [Kui Jia](http://kuijia.site/)</p> ##### <p align="center"> ICCV2023 ##### <p align="center"> *equal contribution #### <p align="center">[Paper](https://fantasia3d.github.io/assets/Fantasia3D.pdf) | [ArXiv](http://arxiv.org/abs/2303.13873) | [Project Page](https://fantasia3d.github.io/) | [Supp_material](https://fantasia3d.github.io/assets/supp_materials.pdf) | [Video](https://www.youtube.com/watch?v=Xbzl4HzFiNo)</p> <p align="center"> <img width="40%" src="assets/head_figure.jpg"/> </p> https://user-images.githubusercontent.com/128572637/fe5a05d3-33af-41c4-a5c0-e74485797f08 https://user-images.githubusercontent.com/128572637/691a1c2d-0c55-4b2e-8dd6-82fddc2685a6 https://user-images.githubusercontent.com/128572637/99ab7e61-eb81-4b75-8138-3321b6633d78 https://user-images.githubusercontent.com/128572637/405fe77e-25c0-410f-b463-e1e3ded2f065 # Update log **Please pull the latest code to improve performance!!** - (2023.10.17) - Add a FAQ about the performance of the official code and the reproduced version of threestudio, i.e. Q8. - (2023.10.13) - Add a FAQ about the problem of over-saturation and over-smoothing appearance, i.e. Q7. - (2023.09.01) - Note: adding negative prompts can improve the visual quality in appearance modeling. See the latest [Gallery](https://github.com/Gorilla-Lab-SCUT/Fantasia3D/issues/19) for more details. - (2023.08.30) - Add two FAQs. - (2023.08.29) - Skip some unnecessary material prediction processes in geometry modeling, which slightly decreases the training time. - (2023.08.22) - Note: For situations where the requirement for the number of mesh faces is not high, I recommend using a DMTet resolution of 128 to achieve a balance between quality and generation speed. When using a resolution of 128 or less, the generation speed will be significantly faster. - (2023.08.20) - Note: different versions of stable diffusion seem to have different performance. In terms of generating avatars, version 1.5 performs better than version 2.1. - (2023.08.11) - Fix the bug about the unsmooth geometry in some cases. - (2023.08.06) - Add a tip to improve the realism of appearance. - (2023.08.05) - Fix the bug about the same seed between different gpus, which may not accelerate convergence. - Add a part for directly performing UV padding in the code, so there is no need for additional operations in the blender. - (2023.07.26) - Fix the bug about using the tangent space normal. # FAQs ***Q1***: *About the use of normal and mask images as the input of stable diffusion model and analysis* Answer: Our initial hypothesis is that normal and mask images, representing local and silhouette information of shapes respectively, can benefit geometry learning. Additionally, we observed that the value range of the normal map is normalized to (-1, 1), which aligns with the data range required for latent space diffusion. Our empirical studies validate this hypothesis. Further support for our hypothesis comes from the presence of normal images in the LAION-5B dataset used for training Stable Diffusion (see [Website](https://rom1504.github.io/clip-retrieval/?back=https%3A%2F%2Fknn.laion.ai&index=laion5B-H-14&useMclip=false&query=normal+map) for retrieval of normal data in LAION-5B). Therefore, the normal data is not considered an out-of-distribution (OOD) input for stable diffusion. To handle rough and coarse geometry in the early stage of learning, we directly utilize concatenated 64 $\times$ 64 $\times$ 4 (normal, mask) images as the latent code, inspired by Latent-NeRF, to achieve better convergence. However, using the normal map without VAE encoding in the world coordinate system may lead to inc
Excerpt of 24,926 characters
Read on GitHub
111
14
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:5a5b2dbd474ec265, topic:text-to-3d, desc:text-to-3d, readme:text-to-3d