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.
We evaluate our method on different datasets (including ShapeNet, CUB-200-2011, and Pascal3D+) and achieve state-of-the-art results, outperforming all the other supervised and unsupervised methods and 3D representations, all in terms of performance, accuracy, and training time.
| Date | Stars |
|---|---|
| 2026-07-24 | 267 |
| 2026-07-25 | 267 |
| 2026-07-28 | 267 |
| 2026-07-30 | 267 |
| 2026-08-06 | 267 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# An Effective Loss Function for Generating 3D Models from Single 2D Image without Rendering
[](https://paperswithcode.com/sota/single-view-3d-reconstruction-on-shapenet?p=an-effective-loss-function-for-generating-3d)
### [Papers with code](https://paperswithcode.com/paper/an-effective-loss-function-for-generating-3d) | [Paper](https://arxiv.org/abs/2103.03390)
[Nikola Zubić](https://www.linkedin.com/in/nikola-zubi%C4%87-50458b18b/) [Pietro Lio](https://www.cl.cam.ac.uk/~pl219/)
University of Novi Sad University of Cambridge
[AIAI 2021](http://www.aiai2021.eu/)
## Citation
Besides AIAI 2021, our paper is in a Springer's book entitled "Artificial Intelligence Applications and Innovations": [link](https://link.springer.com/chapter/10.1007%2F978-3-030-79150-6_25)
<br><br>
Please, cite our paper if you find this code useful for your research.
```
@InProceedings{zubic_aiai_2021,
author="Zubi{\'{c}}, Nikola
and Li{\`o}, Pietro",
title="An Effective Loss Function for Generating 3D Models from Single 2D Image Without Rendering",
booktitle="Artificial Intelligence Applications and Innovations (AIAI)",
year="2021",
publisher="Springer International Publishing",
pages="309--322",
}
```
## Prerequisites
- Download code:<br>
Git clone the code with the following command:
```
git clone https://github.com/NikolaZubic/2dimageto3dmodel.git
```
- Open the project with Conda Environment (Python 3.7)
- Install packages:
```
conda install pytorch torchvision torchaudio cudatoolkit=11.0 -c pytorch
```
Then git clone Kaolin library in the root (2dimageto3dmodel) folder with the following [commit](https://github.com/NVIDIAGameWorks/kaolin/tree/e7e513173bd4159ae45be6b3e156a3ad156a3eb9) and run the following commands:
```
cd kaolin
git checkout e7e513173b
python setup.py install
pip install --no-dependencies nuscenes-devkit opencv-python-headless scikit-learn joblib pyquaternion cachetools
pip install packaging
```
## Run the program
Run the following commands from the root/code/ (2dimageto3dmodel/code/) directory:<br>
```
python main.py --dataset cub --batch_size 16 --weights pretrained_weights_cub --save_results
```
for the CUB Birds Dataset.
<br><br>
```
python main.py --dataset p3d --batch_size 16 --weights pretrained_weights_p3d --save_results
```
for the Pascal 3D+ Dataset.<br><br>
The results will be saved at `2dimageto3dmodel/code/results/` path.
## Continue training
To continue the training process:<br>
Run the following commands (without ```--save_results```) from the root/code/ (2dimageto3dmodel/code/) directory:<br>
```
python main.py --dataset cub --batch_size 16 --weights pretrained_weights_cub
```
for the CUB Birds Dataset.
<br><br>
```
python main.py --dataset p3d --batch_size 16 --weights pretrained_weights_p3d
```
for the Pascal 3D+ Dataset.<br><br>
## Generation of Pseudo-ground-truths
In these reconstruction steps, we need a trained mesh estimation model. We can use the pre-trained model (already provided) or train it from scratch. The Pseudo-ground-truth data for CUB birds is generated in the following way:
```
python run_reconstruction.py --name pretrained_reconstruction_cub --dataset cub --batch_size 10 --generate_pseudogt
```
For Pascal 3D+ dataset:
```
python run_reconstruction.py --name pretrained_reconstruction_p3d --dataset p3d --optimize_z0 --batch_size 10 --generate_pseudogt
```
Through this, we replace a cache directory, which contains pre-computed statistics for the evaluation of Frechet Inception Distances, poses and images metadata, and the Pseudo-ground-truths for eacExcerpt of 5,748 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:eba48cd0eed075dc, topic:computer-vision, topic:3d-reconstruction, readme:3d reconstruction
matched fp:eba48cd0eed075dc, topic:deep-learning, topic:pytorch
matched fp:eba48cd0eed075dc, topic:gan