This repository contains an implementation for performing 3D animal (quadruped) reconstruction from a monocular image or video. The system adapts the pose (limb positions) and shape (animal type/he…

Accelerating tag tracking algorithm "apriltag" using CUDA

Pytorch reimplementation for "Gradient Surgery for Multi-Task Learning"

Convolutional Neural Network for 3D meshes in PyTorch

Pytorch implementation of PCT: Point Cloud Transformer

Jittor implementation of PCT:Point Cloud Transformer

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

[CVPR'19] Dataset and code used in the research project Scan2CAD: Learning CAD Model Alignment in RGB-D Scans

Code repository for paper `Skeleton Merger: an Unsupervised Aligned Keypoint Detector`.

UKPGAN: A General Self-Supervised Keypoint Detector (CVPR2022)

USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds. ICCV 2019

Differentiable Point Cloud Sampling (CVPR 2020 Oral)

MuJoCo Models for Google's Scanned Objects Dataset

Pointfilter: Point Cloud Filtering via Encoder-Decoder Modeling

[ICCV 23] Density-invariant Features for Distant Point Cloud Registration

Kernel Point Convolution implemented in PyTorch

This is an implementation for the paper entitled "Fast mesh denoising with data driven normal filtering using deep variational autoencoders" published in IEEE Transactions on Industrial Informatics…

[CVPR2023] Official Implementation of "DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets"

Rotation-Invariant Transformer for Point Cloud Matching

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

Mesh denoising with graph convolutional networks

CircNet: Meshing 3D Point Clouds with Circumcenter Detection (ICLR2023)

Official code for paper: PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance [ICLR'25]

REPS: Reconstruction-based Point Cloud Sampling

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)…

A Task-driven Network for Mesh Classification and Semantic Part Segmentation