KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#dsh #dsh-plugin #ai-agent #developer-tools #codex #typescript #cli #deepseek-harness #claude-code #ai-agents #mcp #rust

deep-geometric-prior

★ 145 Open GitHub ↗

The reference implementaiton for the paper "Deep Geometric Prior for Surface Reconstruction"

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Deep Geometric Prior for Surface Reconstruction
The reference implementaiton for the CVPR 2019 paper [Deep Geometric Prior for Surface Reconstruction](https://arxiv.org/pdf/1811.10943.pdf).

![](https://github.com/fwilliams/deep-geometric-prior/blob/master/data/teaser.png)

## Code Overview
There are several programs in this repository explained in detail below. The documentation for each program can be seen by running it with the `-h` flag. The code is also extensively commented and should be easy to follow. Please create GitHub issues or reach out to me by email if you run into any problems.

- #### `reconstruct_surface.py`:
  Compute a set of patches which represent a surface.

This program produces a dense point cloud (`out.ply` by default) and a binary file file (`out.pt` by default) which can be used to regenerate the dense point cloud with `export_point_cloud.py` (this is useful for example, if you want to try different sampling densities).
   
- #### `reconstruct_single_patch.py` 
  Compute a single surface patch fitted to a point cloud.

As with `reconstruct_surface.py`, this program produces a file (defaulting to `out.pt`) as output which can be used to upsample a point cloud with `export_point_cloud.py`. You can optionally plot the reconstruction with `plot_reconstruction.py`.
   
- #### `export_point_cloud.py` 
  Exports a dense point cloud (`out.ply` by default) from a reconstruction the `.pt` binary file produced by `reconstruct_surface.py` or `reconstruct_single_patch,py`.

## Setting up and Running the Code
  
### With [`conda`](https://conda.io/en/latest/) (Recommended)
All dependencies can be automatically installed with [`conda`](https://conda.io/en/latest/) using the provided `environment.yml`
Simply run the following from the root of the repository:
  
```
conda env create -f environment.yml
```
  
This will create a conda environment named `deep-surface-prior` with all the correct dependencies installed. You can activate the environment by running:
```
conda activate deep-geometric-prior
```

### Installing Dependencies Manually (Not Recommended)
If you are not using Conda, you can manually install the following dependencies:
- Python 3.6 (or later)
- PyTorch 1.0 (or later)
- NumPy 1.15 (or later)
- SciPy 1.1.0 (or later)
- [FML](https://github.com/fwilliams/fml) 0.1 (or later)
- [Point Cloud Utils](https://github.com/fwilliams/point-cloud-utils) 0.12.0 (or later) 
- [Mayavi](https://docs.enthought.com/mayavi/mayavi/) 4.6.2 (or later)

## Reducing Memory Usage
The Deep Geometric Prior trains an individual MLP for each surface patch in a model. Since there can be a lot of patches in a point cloud, this can lead to a high GPU memory usage when fitting all the MLPs in parallel. For this reason, we provide a `--batch-size` argument to `reconstruct_surface.py` which only fits `--batch-size` MLPs in parallel at once. If you run out of VRAM, try decreasing this parameter.

## [Surface Reconstruction Benchmark Data](https://drive.google.com/file/d/17Elfc1TTRzIQJhaNu5m7SckBH_mdjYSe/view?usp=sharing)
The scans, ground truth data and reconstructions from the paper are [available for download here](https://drive.google.com/file/d/17Elfc1TTRzIQJhaNu5m7SckBH_mdjYSe/view?usp=sharing).

The linked zip archive contains 3 directories:
* `scans` contains a simulated scan of the models. The scans are generated with the [surface reconstruction benchmark](https://github.com/fwilliams/surface-reconstruction-benchmark).
* `ground_truth` contains a dense point cloud for each model sampled from the ground truth surface.
* `our_reconstructions` contains a reconstructed point cloud for each model generated with our method.

## Running the Deep Geometric Prior on the Surface Reconstruction Benchmark
* Make sure to install the project dependencies with conda or manually as described [above](https://github.com/fwilliams/deep-geometric-prior#setting-up-and-running-the-code).
* Download the [Surface Reconstruction Benchmark Data](https://drive.google.com/file/d/17Elfc1TTRzIQJhaNu5m7SckBH_mdjYSe/view?usp=sharing) (See [above](https://github.com/fwilliams/deep-geometric-prior#surface-reconstruction-benchmark-data) section for details).
* Extract the zip file which should produce a directory named `deep_geometric_prior_data`. 
* Since Deep Geometric Prior fits many neural networks over a model, it requires a lot of memory (To reduce memory usage see [section above on memory usage](#reducing-memory-usage)), thus it is best to use multiple GPUs when reconstructing a model. Suppose four GPUs are available named `cuda:0`, `cuda:1`, `cuda:2`, and `cuda:3`, then the following five commands will reconstruct the five benchmark models using those GPUs. You can change the list of devices for different configurations:
```bash
python reconstruct_surface.py deep_geometric_prior_data/scans/gargoyle.ply 0.01 1.0 20 -d cuda:0 cuda:1 cuda:2 cuda:3 -nl 25 -ng 25 -o gargoyle

python reconstruct_surface.py deep_geometric_prior_data/scans/dc.ply 0.01 1.0 20 -d cuda:0 cuda:1 cuda:2 cuda:3 -nl 25 -ng 25 -o dc

python reconstruct_surface.py deep_geometric_prior_data/scans/lord_quas.ply 0.01 1.0 10 -d cuda:0 cuda:1 cuda:2 cuda:3 -nl 25 -ng 25 -o lord_quas

python reconstruct_surface.py deep_geometric_prior_data/scans/anchor.ply 0.01 1.0 10 -d cuda:0 cuda:1 cuda:2 cuda:3 -nl 25 -ng 25 -o anchor

python reconstruct_surface.py deep_geometric_prior_data/scans/daratech.ply 0.01 1.0 10 -d cuda:0 cuda:1 cuda:2 cuda:3 -nl 25 -ng 25 -o daratech   
```
*NOTE:* You may need to change the paths `deep_geometric_prior_data/scans/*.ply` to point to where you extracted the zip file, and you may need to change the device arguments `-d cuda:0 ...` to adapt to your system. To avoid `CUDA out of memory` error use the reconstruction in batches `--batch-size`.

Each of the above commands produces a `ply` file and `pt` file (e.g. `anchor.ply`, `anchor.pt`). The PLY file contains a dense upsampled point cloud and the PT file contains metadata about the reconstruction. You can use the PT file to perform further operations using example `export_point_cloud.py`.

deep-geometric-prior

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README