Pointcept: a codebase for point cloud perception research. Latest works: PTv3 (CVPR'24 Oral), PPT (CVPR'24), OA-CNNs (CVPR'24), MSC (CVPR'23)

[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)

End-to-End Object Detection with Transformers

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.

[CVPR2024] OneFormer3D: One Transformer for Unified Point Cloud Segmentation

Surface and Edge Detection for Primitive Fitting of Point Clouds，SIGGRAPH 2023

Code base of ParSeNet: ECCV 2020.

Source code for "Supervised Fitting of Geometric Primitives to 3D Point Clouds" [CVPR 2019].

[ICCV 2021] "HPNet: Deep Primitive Segmentation Using Hybrid Representations"

Associatively Segmenting Instances and Semantics in Point Clouds, CVPR 2019

Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D Semantic Segmentation with Superpoint Transformer" and SuperCluster introduced in [3DV'24 Oral] "Scal…

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

Segmentator for clustering on meshes or pointclouds

ABC: A Big CAD Model Dataset For Geometric Deep Learning

Python wrapper around C++ utilities for computing neighbors and local geometric features of a point cloud

Fast and memory-efficient exact attention

PyTorch Extension Library of Optimized Scatter Operations

DeepVision3D is an open source toolbox for point-cloud understanding.

Official Implementation for "Mask-Attention-Free Transformer for 3D Instance Segmentation"

PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).

A PyTorch Library for Multi-Task Learning

This is the source code for the ECCV paper "MTFormer: Multi-Task Learning via Transformer and Cross-Task Reasoning"

(CVPR 2022) MulT: An End-to-End Multitask Learning Transformer

Official implementation of "Multi-Task Learning as a Bargaining Game" [ICML 2022]

Official PyTorch Implementation for Conflict-Averse Gradient Descent (CAGrad)

Official PyTorch Implementation for Fast Adaptive Multitask Optimization (FAMO)