A PyTorch Library for Accelerating 3D Deep Learning Research
-
Updated
Aug 9, 2024 - Python
A PyTorch Library for Accelerating 3D Deep Learning Research
🔥[IEEE TPAMI 2020] Deep Learning for 3D Point Clouds: A Survey
NVIDIA Kaolin Wisp is a PyTorch library powered by NVIDIA Kaolin Core to work with neural fields (including NeRFs, NGLOD, instant-ngp and VQAD).
pyntcloud is a Python library for working with 3D point clouds.
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
3DMatch - a 3D ConvNet-based local geometric descriptor for aligning 3D meshes and point clouds.
[ECCV'20] Convolutional Occupancy Networks
This repository contains the code for the CVPR 2020 paper "Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision"
Fuse multiple depth frames into a TSDF voxel volume.
This repository contains the source codes for the paper "AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation ". The network is able to synthesize a mesh (point cloud connectivity) from a low-resolution point cloud, or from an image.
[ECCV 2020] Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social distancing, and body orientation.
Pytorch code to construct a 3D point cloud model from single RGB image.
KITTI data processing and 3D CNN for Vehicle Detection
3D Object Detection for Autonomous Driving in PyTorch, trained on the KITTI dataset.
[CVPR'23] Learning Neural Parametric Head Models
Research platform for 3D object detection in PyTorch.
[Siggraph '23] NeRSemble: Neural Radiance Field Reconstruction of Human Heads
[ICCVW-2021] SA-Det3D: Self-attention based Context-Aware 3D Object Detection
[AAAI'20] LCD: Learned Cross-Domain Descriptors for 2D-3D Matching
Add a description, image, and links to the 3d-deep-learning topic page so that developers can more easily learn about it.
To associate your repository with the 3d-deep-learning topic, visit your repo's landing page and select "manage topics."