eg3d
Clip-Forge
| eg3d | Clip-Forge | |
|---|---|---|
| 10 | 6 | |
| 3,124 | 360 | |
| 0.6% | 0.0% | |
| 0.0 | 0.0 | |
| 11 months ago | over 1 year ago | |
| Python | Python | |
| GNU General Public License v3.0 or later | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
eg3d
-
Synthesized 360 views of Stable Diffusion generated photos with PanoHead
It's based on this, which has cats https://github.com/NVlabs/eg3d
-
2D to 3D easily
EG3D is not a new idea, but developers claim that it works significantly faster and more effective than other neural networks. It is open source, you can test it on GitHub (https://github.com/NVlabs/eg3d).
- Who is building StableDiffusion/DALL-E but for 3D assets?
- [D] Diffusers applied to 3D model generation
- EG3D: Efficient Geometry-aware 3D Generative Adversarial Networks
-
Researchers at Stanford have developed an Artificial Intelligence (AI) model, EG3D, that can generate random images of faces and other objects with high resolution together with underlying geometric structures
Continue reading | Checkout the paper, github
- unresolved external symbol while running eg3d code
-
[D] NVlabs finally released the code for EG3D, but no inversion script?
So we can finally play around with the cool NVLabs EG3D, but they refuse to release the inversion script.
- EG3D: Efficient Geometry-Aware 3D Generative Adversarial Networks
Clip-Forge
-
Hypothesis to create "easy" 3D models
There are publications out recently about deep research into directly generating 3d objects from a text prompt like DreamFusion3D and CLIP-Forge, a lot of progress has been made in this area so there are things you can learn from these approaches.
- Make-A-Video is a state-of-the-art AI system that generates videos from text
- Who is building StableDiffusion/DALL-E but for 3D assets?
- [D] Diffusers applied to 3D model generation
- So how long before something like this can generate a 3d model?
- 3D Shapes Generated using CLIP-Forge
What are some alternatives?
stylegan-xl - [SIGGRAPH'22] StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
text2mesh - 3D mesh stylization driven by a text input in PyTorch
PanoHead - Code Repository for CVPR 2023 Paper "PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360 degree"
make-a-video-pytorch - Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch
text2voxels - Generate 3D voxels from text with AI
CenterSnap - Pytorch code for ICRA'22 paper: "Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation"
PanoHead - Code Repository for CVPR 2023 Paper "PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360 degree"
ml-gmpi - Official PyTorch implementation of GMPI (ECCV 2022, Oral Presentation)
NeROIC
jukebox - Code for the paper "Jukebox: A Generative Model for Music"