All Projects → kumuji → volumentations

kumuji / volumentations

Licence: MIT License
Augmentation package for 3d data based on albumentaitons

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to volumentations

Point Cloud Utils
A Python library for common tasks on 3D point clouds
Stars: ✭ 281 (+980.77%)
Mutual labels:  point-cloud, mesh
Kinectfusionapp
Sample implementation of an application using KinectFusionLib
Stars: ✭ 69 (+165.38%)
Mutual labels:  point-cloud, mesh
Easy3d
A lightweight, easy-to-use, and efficient C++ library for processing and rendering 3D data
Stars: ✭ 383 (+1373.08%)
Mutual labels:  point-cloud, mesh
Kinectfusionlib
Implementation of the KinectFusion approach in modern C++14 and CUDA
Stars: ✭ 261 (+903.85%)
Mutual labels:  point-cloud, mesh
Meshlab
The open source mesh processing system
Stars: ✭ 2,619 (+9973.08%)
Mutual labels:  point-cloud, mesh
Draco
Draco is a library for compressing and decompressing 3D geometric meshes and point clouds. It is intended to improve the storage and transmission of 3D graphics.
Stars: ✭ 4,611 (+17634.62%)
Mutual labels:  point-cloud, mesh
3d Machine Learning
A resource repository for 3D machine learning
Stars: ✭ 7,405 (+28380.77%)
Mutual labels:  point-cloud, mesh
3dhop
3D Heritage Online Presenter
Stars: ✭ 89 (+242.31%)
Mutual labels:  point-cloud, mesh
Openmvs
open Multi-View Stereo reconstruction library
Stars: ✭ 1,842 (+6984.62%)
Mutual labels:  point-cloud, mesh
Polylidar
Polylidar3D - Fast polygon extraction from 3D Data
Stars: ✭ 106 (+307.69%)
Mutual labels:  point-cloud, mesh
Point2Mesh
Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance (ECCV2020)
Stars: ✭ 61 (+134.62%)
Mutual labels:  point-cloud, mesh
PointCutMix
our code for paper 'PointCutMix: Regularization Strategy for Point Cloud Classification'
Stars: ✭ 42 (+61.54%)
Mutual labels:  point-cloud, data-augmentation
fastai sparse
3D augmentation and transforms of 2D/3D sparse data, such as 3D triangle meshes or point clouds in Euclidean space. Extension of the Fast.ai library to train Sub-manifold Sparse Convolution Networks
Stars: ✭ 46 (+76.92%)
Mutual labels:  mesh, data-augmentation
RealSense
Extension of RealSense Unity Wrapper [Unofficial]
Stars: ✭ 31 (+19.23%)
Mutual labels:  point-cloud
cloud to map
Algorithm that converts point cloud data into an occupancy grid
Stars: ✭ 26 (+0%)
Mutual labels:  point-cloud
Tensorflow-data-loader
Reading data into tensorflow using tf.data function
Stars: ✭ 15 (-42.31%)
Mutual labels:  data-augmentation
mixup
speechpro.com/
Stars: ✭ 23 (-11.54%)
Mutual labels:  data-augmentation
lepcc
Point Cloud Compression used in i3s Scene Layer Format
Stars: ✭ 22 (-15.38%)
Mutual labels:  point-cloud
sp segmenter
Superpixel-based semantic segmentation, with object pose estimation and tracking. Provided as a ROS package.
Stars: ✭ 33 (+26.92%)
Mutual labels:  point-cloud
point-cloud-prediction
Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks
Stars: ✭ 97 (+273.08%)
Mutual labels:  point-cloud

Tests Codecov PyPI Documentation Status Code Style: Black Downloads CodeFactor Maintainability

logo Volumentations

augmented_teapot

Python library for 3d data augmentaiton. Hard fork from alumentations.

For more information on available augmentations check documentation.

Or, check simple example in colab: Open In Colab

Setup

pip install volumentations

Usage example

import volumentations as V
import numpy as np

augmentation = V.Compose(
    [
        V.Scale3d(scale_limit=(0.2, 0.2, 0.1), p=0.75),
        V.OneOrOther(
            V.Compose(
                [
                    V.RotateAroundAxis3d(
                        rotation_limit=np.pi, axis=(0, 0, 1), always_apply=True
                    ),
                    V.RotateAroundAxis3d(
                        rotation_limit=np.pi / 3, axis=(0, 1, 0), always_apply=True
                    ),
                    V.RotateAroundAxis3d(
                        rotation_limit=np.pi / 3, axis=(1, 0, 0), always_apply=True
                    ),
                ],
                p=1,
            ),
            V.Flip3d(axis=(0, 0, 1)),
        ),
        V.OneOf(
            [
                V.RandomDropout3d(dropout_ratio=0.2, p=0.75),
                V.RandomDropout3d(dropout_ratio=0.3, p=0.5),
            ]
        ),
    ]
)

augmented_teapot = augmentation(points=teapot.copy())["points"]
show_augmentation(teapot, augmented_teapot)
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].