Skip to main content

3D gaussian splatting recosntruction

Project description

Gaussian Reconstruction

Gaussian Reconstruction is a Python package for 3D Gaussian splatting reconstruction from video inputs, designed for efficient and high-quality 3D model generation.

Installation and Setup

Follow these steps to set up the environment and install the package.

Step 1: Create the Conda Environment

First, create the gaussian_splatting environment using the provided environment.yml file:

conda env create -f gsrecon/environment.yml

Step 2: Activate the Environment

Activate the newly created environment:

conda activate gaussian_splatting

Step 3: Install Gaussian Reconstruction Package

Install the gaussian-reconstruction package using pip:

pip install gaussian-reconstruction

Additional Dependencies

To ensure successful operation, the following dependencies are required (these are included in the package requirements, but you may install them manually if needed):

  • OpenCV (cv2): pip install opencv-python
  • PyColmap: pip install pycolmap

Usage

Once the package is installed, you can start the conversion process.

Import the Library

Import the VideoToPLYConverter class from the package:

from gsrecon.converter import VideoToPLYConverter

Create a Converter Instance

Create an instance of VideoToPLYConverter with the desired method (e.g., pycolmap):

converter = VideoToPLYConverter(method='pycolmap')

Start converting

Use the convert_video_to_ply function to start the conversion process. Provide the path to the video file and set the extraction rate (frames per second):

video_path = "path/to/your/video.mp4"  # Replace with your video file path
extraction_rate = None  # Set the frame extraction rate; defaults to None (extract all frames unless specified, e.g., 1 for 1 FPS)
converter.convert_video_to_ply(video_path, extraction_rate)

License

This project is licensed under the terms specified in the LICENSE file.


This documentation provides a step-by-step guide to installing, setting up, and using the Gaussian Reconstruction package for 3D Gaussian splatting reconstruction.



Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gaussian-reconstruction-1.2.2.tar.gz (7.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

gaussian_reconstruction-1.2.2-py3-none-any.whl (8.6 kB view details)

Uploaded Python 3

File details

Details for the file gaussian-reconstruction-1.2.2.tar.gz.

File metadata

  • Download URL: gaussian-reconstruction-1.2.2.tar.gz
  • Upload date:
  • Size: 7.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.10.5

File hashes

Hashes for gaussian-reconstruction-1.2.2.tar.gz
Algorithm Hash digest
SHA256 ad74223ea9401f33631e9b33f2d3c27a5bbefa99a7ec190284d4b100cf06fcc7
MD5 a035bb5a46b8a55a8abea98154947eda
BLAKE2b-256 9adecdfad6adb8ee88bfbf1a5f19e2eed8d1c26342e86e9fbcea9c1297e0cbac

See more details on using hashes here.

File details

Details for the file gaussian_reconstruction-1.2.2-py3-none-any.whl.

File metadata

File hashes

Hashes for gaussian_reconstruction-1.2.2-py3-none-any.whl
Algorithm Hash digest
SHA256 9a0a141af8b486db6f14cd57ff74ac4796ab5e24ee3f14d13005293a22121770
MD5 7e959c516590885978d6aaba330a40b7
BLAKE2b-256 a26bc06e640276359c3a2e1c9d7341044939c778e3ace2a41bc1a16b1119efde

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page