Pytorch framework for doing deep learning on point clouds.
-
Updated
Feb 3, 2025 - Python
Pytorch framework for doing deep learning on point clouds.
PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)
[ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions
Point-NeRF: Point-based Neural Radiance Fields
[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies
[CVPR2024] OneFormer3D: One Transformer for Unified Point Cloud Segmentation
[CVPR 2022 Oral] SoftGroup for Instance Segmentation on 3D Point Clouds
[CVPR 2022 Oral] Official implementation for "Surface Representation for Point Clouds"
4D Spatio-Temporal Semantic Segmentation on a 3D video (a sequence of 3D scans)
LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs (CVPR 2023)
Grid-GCN for Fast and Scalable Point Cloud Learning
[ECCV'20] Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation
CVPR 2020, "FPConv: Learning Local Flattening for Point Convolution"
FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image
This work is based on our paper "DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes", which appeared at the IEEE Conference On Computer Vision And Pattern Recognition (CVPR) 2020.
[AAAI2025] UniDet3D: Multi-dataset Indoor 3D Object Detection
[CVPR 2024] Memory-based Adapters for Online 3D Scene Perception
[ECCV 2024] 3D Small Object Detection with Dynamic Spatial Pruning
TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes
[ICLR 2025] Official code of "Segment any 3D Object with Language"
Add a description, image, and links to the scannet topic page so that developers can more easily learn about it.
To associate your repository with the scannet topic, visit your repo's landing page and select "manage topics."