2dimageto3dmodel
surface_normal_uncertainty
Our great sponsors
| 2dimageto3dmodel | surface_normal_uncertainty | |
|---|---|---|
| 1 | 1 | |
| 265 | 196 | |
| - | - | |
| 3.7 | 10.0 | |
| about 2 months ago | over 1 year ago | |
| Python | Python | |
| - | MIT License |
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.
2dimageto3dmodel
-
What's the best software for making an interactable 3D app?
As for the app, I feel like I have a really good and unique idea so I don't want to explain it very thoroughly, but essentially I want it to be available on my website and on the app store. Ideally, I want it to scale up and become something big, I feel the scalability for the idea is pretty good so I would hope it doesn't stay a small project. Another specificity that I feel is important is that I want to take a series of 2D images and turn it into a 3D model that can then be manipulated and deformed. There are libraries on GitHub for predictively turning a 2D image into a 3D render like here. I have a hunch this would be incredibly difficult and time-consuming to turn into an app, but I wonder if something like this could even be implemented in unity. I haven't used much GitHub really at all though, and I'm not even sure whether or not I could use someone's code like this on an app and then profit off of it legally, I'm just trying to understand all of this.
surface_normal_uncertainty
-
Non official colab to create normal maps using "Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation" from baegwangbin
I needed normal maps for my movie and I saw in the new ControlNet update that they used https://github.com/baegwangbin/surface_normal_uncertainty to make normals which gave me better results than previous methods. So I decided to make a colab to process all my images because I didn't find how to do it in Automatic 1111.
What are some alternatives?
pix2pixHD - Synthesizing and manipulating 2048x1024 images with conditional GANs
fortuna - A Library for Uncertainty Quantification.
Pix2Vox - The official implementation of "Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images". (Xie et al., ICCV 2019)
IGR - Implicit Geometric Regularization for Learning Shapes
3D-Machine-Learning - A resource repository for 3D machine learning
ipme - An interactive visualization tool that transforms probabilistic programming models into an "Interactive Probabilistic Models Explorer".
APDrawingGAN - Code for APDrawingGAN: Generating Artistic Portrait Drawings from Face Photos with Hierarchical GANs (CVPR 2019 Oral)
DIML - [ICCV 2021] Towards Interpretable Deep Metric Learning with Structural Matching
neural-deferred-shading - Multi-View Mesh Reconstruction with Neural Deferred Shading (CVPR 2022)
polygonjs - node-based WebGL design tool
calibrated-backprojection-network - PyTorch Implementation of Unsupervised Depth Completion with Calibrated Backprojection Layers (ORAL, ICCV 2021)