[CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training

Official Implementation for "Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures"

A clean, compact renderer for spherical images of shapenet objects in blender <2.8.

Canonical Capsules: Self-Supervised Capsules in Canonical Pose (NeurIPS 2021)

A list of papers about point clouds registration

A Graph Neural Network Library in Jax

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

Pytorch implementation of DiffusionNet for fast and robust learning on 3D surfaces like meshes or point clouds.

Simple implementation of mean shift clustering in python

[ECCV-20] Official PyTorch implementation of HoughNet, a voting-based object detector.

A list of resources about deep learning solutions on 3D shape processing

My Python Examples

Starter kit for the CVPR 2020 RANSAC tutorial benchmark

Code release for ICCV 2019 Oral, "Linearized Multi-Sampling for Differentiable Image Transformation"

Code release for WACV 2020, "Optimizing Through Learned Errors for Accurate Sports Field Registration"

Code Release for CVPR 2020, "ACNe: Attentive Context Normalizationfor Robust Permutation-Equivariant Learning"

A list of papers and datasets about point cloud analysis (processing)

A machine learning project for learning geospatial topology for the paper on https://arxiv.org/abs/1806.03857

PyTorch for Numpy users. https://pytorch-for-numpy-users.wkentaro.com

3D reconstruction, sfm with Python3

A Python toolbox for performing gradient-free optimization

a distributed Hyperband implementation on Steroids

Bayesian Optimization of Combinatorial Structures

Distributed Asynchronous Hyperparameter Optimization in Python

Parallelised Thompson Sampling in GPs for Bayesian Optimisation

Spearmint is a package to perform Bayesian optimization according to the algorithms outlined in the paper: Practical Bayesian Optimization of Machine Learning Algorithms. Jasper Snoek, Hugo Laroche…

A Python implementation of global optimization with gaussian processes.