ThibaultGROUEIX

HY3D-Bench. Python

fpo. Implementation of Flow Policy Optimization (FPO)

poissonnet. Official repository for "PoissonNet: A Local-Global Approach for Learning on Surfaces"

FramePack. Lets make video diffusion practical!

Instant3dit. Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects (CVPR 2025)

dust3r. DUSt3R: Geometric 3D Vision Made Easy

TutteNet. Python

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

textile. Official repository of "TexTile: A Differentiable Metric for Texture Tileability" [CVPR 2024]

continuous_3d_words_code. Jupyter Notebook

EscherNet. [CVPR2024 Oral] EscherNet: A Generative Model for Scalable View Synthesis

LLaVA. [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

gigapose. [CVPR 2024] PyTorch implementation of GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence

DreamCraft3D. [ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

Wonder3D. Single Image to 3D using Cross-Domain Diffusion for 3D Generation

author-kit. TeX

carbontracker. Track and predict the energy consumption and carbon footprint of training deep learning models.

sdfstudio. A Unified Framework for Surface Reconstruction

Awesome-CLIP. Awesome list for research on CLIP (Contrastive Language-Image Pre-Training).

threestudio. A unified framework for 3D content generation.

Caption-Anything. Caption-Anything is a versatile tool combining image segmentation, visual captioning, and ChatGPT, generating tailored captions with diverse controls for user preferences. https://huggingface.co/spaces/TencentARC/Caption-Anything https://huggingface.co/spaces/VIPLab/Caption-Anything

TextDeformer. Python

Mosaic. Simple greedy image packing

IF. Python

Anything-3D. Segment-Anything + 3D. Let's lift anything to 3D.

PerspectiveFields. [CVPR 2023 Highlight] Perspective Fields for Single Image Camera Calibration

ivid. PyTorch implementation of the ICCV paper "3D-aware Image Generation using 2D Diffusion Models"

nope. [CVPR 2024] PyTorch implementation of NOPE: Novel Object Pose Estimation from a Single Image

ControlNet. Let us control diffusion models!

zero123. Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)

optimate. A collection of libraries to optimise AI model performances

LAVIS. LAVIS - A One-stop Library for Language-Vision Intelligence

RDM-Region-Aware-Diffusion-Model. Python

megapose6d. Code for "MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare", CoRL 2022.

sjc. Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation (CVPR 2023)

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

imagen-pytorch. Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

marcel. Le docker français :whale: :fr:

template-pose. [CVPR 2022] Pytorch implementation of "Templates for 3D Object Pose Estimation Revisited: Generalization to New objects and Robustness to Occlusions" paper

NeuralJacobianFields. Python

disparityprojection. Python

laion-3d. Collect large 3d dataset and build models

continuous-remeshing. Continuous Remeshing For Inverse Rendering

lambda-diffusers. Jupyter Notebook

model-viewer. Easily display interactive 3D models on the web and in AR!

stable-dreamfusion. Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

nerfstudio. A collaboration friendly studio for NeRFs

GET3D. Python

ManifoldPlus. ManifoldPlus: A Robust and Scalable Watertight Manifold Surface Generation Method for Triangle Soups

nerf-factory. An awesome PyTorch NeRF library

neural-implicit-queries. Queries on neural implicit surfaces via range analysis: ray casting, intersection, closest point, & more. SIGGRAPH 2022 paper. JAX implementation.

CLIP-Mesh. Official implementation of CLIP-Mesh: Generating textured meshes from text using pretrained image-text models

nvdiffrast. Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering

stable-diffusion. A latent text-to-image diffusion model

DIS. This is the repo for our new project Highly Accurate Dichotomous Image Segmentation

gradient_descent_viz. interactive visualization of 5 popular gradient descent methods with step-by-step illustration and hyperparameter tuning UI

mesh-signatures. A small project implementing different per-vertex mesh signatures.

U-2-Net. The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

fiftyone. Refine high-quality datasets and visual AI models

cholespy. An easily integrable Cholesky solver on CPU and GPU

llvm-project. The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

johnnydep. Display dependency tree of Python distribution

Scientific-Inkscape. Scientific Inkscape: Inkscape extensions for figure resizing and editing

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

tiny-cuda-nn. Lightning fast C++/CUDA neural network framework

instant-ngp. Instant neural graphics primitives: lightning fast NeRF and more

globalSpeed. Web extension to set a default speed for video and audio

torchshow. Visualize PyTorch tensors with a single line of code.

DeepViewAgg. [CVPR'22 Best Paper Finalist] Official PyTorch implementation of the method presented in "Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation"

posebert. Python

ROMP. Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]

CLIPasso. Jupyter Notebook

polyscope. A C++ & Python viewer for 3D data like meshes and point clouds

focalpose. [CVPR 2022] Focal Length and Object Pose Estimation via Render and Compare

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

open_clip. An open source implementation of CLIP.

ROCA. Official code for ROCA: Robust CAD Model Retrieval and Alignment from a Single Image (CVPR 2022)

nanobind. nanobind: tiny and efficient C++/Python bindings

mesh_to_sdf. Calculate signed distance fields for arbitrary meshes

shapegan. Generative Adversarial Networks and Autoencoders for 3D Shapes

scaper. A library for soundscape synthesis and augmentation

immobilier-paris. How is Paris housing's price evolving? Small data wrangling and analysis.

PyMeshLab. The open source mesh processing python library

NeuralWarp. Code release of paper Improving neural implicit surfaces geometry with patch warping

svox2. Plenoxels: Radiance Fields without Neural Networks

MoPA. An Blender addon uses ROMP to extract human's 3D poses from image, video or webcam and drive your own 3D character.

SegSwap. (CVPRW 2022) Learning Co-segmentation by Segment Swapping for Retrieval and Discovery

go-ethereum. Go implementation of the Ethereum protocol

moderngl. Modern OpenGL binding for Python

NeuralPull. Implementation of ICML'2021:Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces

ohmyzsh. 🙃 A delightful community-driven (with 2,500+ contributors) framework for managing your zsh configuration. Includes 300+ optional plugins (rails, git, macOS, hub, docker, homebrew, node, php, python, etc), 140+ themes to spice up your morning, and an auto-update tool that makes it easy to keep up with the latest updates from the community.

neuralpull-pytorch. The pytorch implementation of Neural-Pull

detectron2. Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

vnn. Vector Neurons: A General Framework for SO(3)-Equivariant Networks

Thea. A toolkit for visual computing with a focus on geometry processing

line-surface-reconstruction. Implementation for the "Surface Reconstruction from 3D Line Segments" paper.

PVT. Official implementation of PVT series

tsne-cuda. GPU Accelerated t-SNE for CUDA with Python bindings

NARUTO-HandSignDetection. 物体検出を用いてNARUTOの印(子～亥、壬、合掌)を検出するモデルとサンプルプログラムです。このリポジトリでは、YOLOXを使用しています(This is a model and sample program that detects NARUTO's hand sign using object detection. This repository use YOLOX.)

idr. Python

awesome-NeRF. A curated list of awesome neural radiance fields papers

DeepImplicitTemplates. Implementation of "Deep Implicit Templates for 3D Shape Representation"

nerf-pytorch. A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

Implicit_Dense_Correspondence. Python

eft. visualization code for 3D human body annotation by EFT (Exemplar Fine-tuning)

frankmocap. A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

byol-pytorch. Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch

ContactPose. Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images.

detr. End-to-End Object Detection with Transformers

dope. Python

FewShotViewpoint. (ECCV 2020) PyTorch implementation of paper "Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild"

dti-clustering. (NeurIPS 2020 oral) Code for "Deep Transformation-Invariant Clustering" paper

google-research. Google Research

RANSAC-Flow. (ECCV 2020) RANSAC-Flow: generic two-stage image alignment

VaDE-pytorch. the reproduce of Variational Deep Embedding : A Generative Approach to Clustering Requirements by pytorch

SpectralNet. Deep network that performs spectral clustering

DeepClustering. Methods and Implements of Deep Clustering

hierarchical_primitives. Code for "Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image", CVPR 2020

pytorch-lightning. Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

depth2time. code for reproducing our interactive art installation "Do silhouettes dream?"

interview-prep. Notes on preparing for coding interviews during my PhD

openMVG. open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.

COVID-19. Novel Coronavirus (COVID-19) Cases, provided by JHU CSSE

kaolin. A PyTorch Library for Accelerating 3D Deep Learning Research

pytorch3d. PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

MVA_2019_SL.

scene-representation-networks. Official Pytorch implementation of Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations

doc3D-dataset. A hybrid dataset for document unwarping (Paper: https://www3.cs.stonybrook.edu/~cvl/projects/dewarpnet/storage/paper.pdf)

xnocs. Multiview Aggregation for Learning Category-Specific Shape Reconstruction, NeurIPS 2019

MSN-Point-Cloud-Completion. Morphing and Sampling Network for Dense Point Cloud Completion (AAAI2020)

StyleGAN2_PyTorch. StyleGAN2 PyTorch 1.0.1

parsynt. Automatic parallel divide-and-conquer programs synthesizer

Flaubert. Unsupervised Language Model Pre-training for French

csm. Code release for "Canonical Surface Mapping via Geometric Cycle Consistency"

chamferdist. Pytorch package to compute Chamfer distance between point sets (pointclouds).

Pixel2MeshPlusPlus. [ICCV2019] Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation.

IIC. Invariant Information Clustering for Unsupervised Image Classification and Segmentation

abc-dataset. ABC: A Big CAD Model Dataset For Geometric Deep Learning

ChamferDistancePytorch. Chamfer Distance in Pytorch with f-score

netvision. JavaScript

gl-recons-viewer. OpenGL Viewer for 3D Reconstruction

ArtMiner. (CVPR 2019) Pytorch implementation of paper "Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning"

Detectron. FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

neural_renderer. A PyTorch port of the Neural 3D Mesh Renderer

demosaicnet_caffe. An implementation of Deep Joint Demosaicking and Denoising - SiGGRAPH Asia 2016

xform_recipes. C++

demosaicnet. A minimal torch implementation of [Gharbi2016]

demosaicnet_torch. Python

hdrnet_legacy. An implementation of 'Deep Bilateral Learning for Real-Time Image Enhancements', SIGGRAPH 2017

hdrnet. An implementation of 'Deep Bilateral Learning for Real-Time Image Enhancement', SIGGRAPH 2017

ALGO1-Info1-2019. :fr: :snake: Des notebooks en Python pour montrer quelques algorithmes pour le cours ALGO1 au département Informatique de l'ENS de Rennes, en automne 2019

AtlasNetV2. This repository contains the source codes for the paper AtlasNet V2 - Learning Elementary Structures.

ObjectPoseEstimationSummary. Resources (papers, datasets, rendering methods) in the domain of object pose estimation.

useful-computer-vision-phd-resources. Lists of resources useful for my PhD in computer vision

photometric-mesh-optim. Photometric Mesh Optimization for Video-Aligned 3D Object Reconstruction :globe_with_meridians: (CVPR 2019)

deep-geometric-prior. The reference implementaiton for the paper "Deep Geometric Prior for Surface Reconstruction"

manopth. MANO layer for PyTorch, generating hand meshes as a differentiable layer

obman. [cvpr19] Hands+Objects synthetic dataset, instructions to download and code to load the dataset

obman_train. [cvpr19] Demo, training and evaluation code for generating dense hand+object reconstructions from single rgb images

CycleConsistentDeformation. This repository contains the source codes for the paper "Unsupervised cycle-consistent deformation for shape matching".

DISN. DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

3DN. 3DN: 3D Deformation Network, CVPR 2019

PointCNN.Pytorch. A PyTorch implemetation of PointCNN (CS294-131 Course Proj)

pixel-cnn-pp. Pytorch Implementation of OpenAI's PixelCNN++

occupancy_networks. This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"

superquadric_parsing. Code for "Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids", CVPR 2019

BMVCTemplate. Paper template and author instructions for BMVC

weakalign. End-to-end weakly-supervised semantic alignment

cnngeometric_pytorch. CNNGeometric PyTorch implementation

cnngeometric_matconvnet. CNNGeometric MatConvNet implementation

ncnet. PyTorch code for Neighbourhood Consensus Networks

cpython. The Python programming language

fml. FML (Francis' Machine-Learnin' Library) - A collection of utilities for machine learning tasks

Pointnet2_PyTorch. PyTorch implementation of Pointnet2/Pointnet++

global-divergences. MMD, Hausdorff and Sinkhorn divergences scaled up to 1,000,000 samples.

geomloss. Geometric loss functions between point clouds, images and volumes

point-cloud-utils. An easy-to-use Python library for processing and manipulating 3D point clouds and meshes.

world-models. Reimplementation of World-Models (Ha and Schmidhuber 2018) in pytorch

pyrender. Easy-to-use glTF 2.0-compliant OpenGL renderer for visualization of 3D scenes.

PyRenderer. 3D Geometry Renderer for Python

shape_sdf. Python

kinetics_i3d_pytorch. Inflated i3d network with inception backbone, weights transfered from tensorflow

pyrender_sdf. Minimal rendering in python for shapes defined implicitely through signed distance functions

cmr. Project repo for Learning Category-Specific Mesh Reconstruction from Image Collections

Chasse-aux-tresors-au-Musee-des-Beaux-Arts-pour-mes-26-ans. 📑 Livrets d'énigmes, utilisés lors de la 🖼 📸 chasse aux trésors qu'on a organisé au musée des Beaux Arts de Rennes pour mes 26 ans 🎂

dgcnn. Python

RenderNet. Code for RenderNet: A deep convolutional network for differentiable rendering from 3D shapes

AttractioNet. Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization

FewShotWithoutForgetting. Python

FeatureLearningRotNet. Python

mrcnn-object-detection. Object detection via a multi-region & semantic segmentation-aware CNN model

LocNet. LocNet: Improving Localization Accuracy for Object Detection

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

PCSNet. a deep learning framework for point cloud segmentation

metro-. Splitted metro distance between 2 meshes (precision, completeness)

photoshape. PLpgSQL

graph_nets. Build Graph Nets in Tensorflow

superpoint_graph. Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

advisor. Open-source implementation of Google Vizier for hyper parameters tuning

mpc.pytorch. A fast and differentiable model predictive control (MPC) solver for PyTorch.