[MICCAI 2019 Young Scientist Award] [MedIA Best Paper Award] Models Genesis: self-supervised pre-training for 3D medical images. Learns transferable representations from unlabeled CT and MRI volumes, then fine-tunes for downstream segmentation and classification. Keras and PyTorch weights included.
- fine-tuning
- representation-learning
- transfer-learning
- self-supervised-learning
[PyTorch] Official implementation of CVPR2022 paper "TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers". https://arxiv.org/abs/2203.11496
Simple and easily configurable 3D FPS-game-like environments for reinforcement learning
[CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing
[ECCV 2024] InstructIR: High-Quality Image Restoration Following Human Instructions https://huggingface.co/spaces/marcosv/InstructIR
Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
[ICCV 2025] Official code of DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
- 3d
- aigc
- dpo
- generative-model
Fully Convolutional Geometric Features: Fast and accurate 3D features for registration and correspondence.
- 3d
- feature-extraction
- correspondence
- fully-convolutional
Official PyTorch implementation of "I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image", ECCV 2020
A no-code 3D playground to explore, design, and interact with Agentic AI systems
A 3D electromagnetic FDTD simulator written in Python with optional GPU support
Official Pytorch implementation of "Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose", ECCV 2020
- single-view
- graph-convolutional-network
- 3d-mesh
- 2d-human-pose
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) from a low-resolution point cloud, or from an image.
An experimental webgl gallery that can visualize tens of thousands of film posters as a voronoi diagram
Machine learning Guide. Learn all about Machine Learning Tools, Libraries, Frameworks, Large Language Models (LLMs), and Training Models.
This repository contains the implementation of paper Online 3D Bin Packing with Constrained Deep Reinforcement Learning.
- 3d-packing
- bin-packing
- online-packing
- packing-algorithm
[指纹浏览器] Simprint is an open-source fingerprint browser and programmable browser workspace designed for isolated environments, automation workflows, proxy orchestration, and browser fingerprint research.
- automation
- browser-automation-workflow
- browser-fingerprint
- browser-runtime
one sentence generates any graph
Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.
- human-pose-estimation
- real-time
- 3d-human-pose
- multi-person-pose-estimation
Library for faster pinned CPU <-> GPU transfer in Pytorch
- cpu-pinned-tensors
- pytorch-variables
- gpu-transfer
- cuda-variables
Official PyTorch implementation of "Expressive Whole-Body 3D Gaussian Avatar", ECCV 2024.
C++ header-only library with methods to efficiently encode/decode Morton codes in/from 2D/3D coordinates
- morton
- c-plus-plus
- encoding
- decoding
nnDetection is a self-configuring framework for 3D (volumetric) medical object detection which can be applied to new data sets without manual intervention. It includes guides for 12 data sets that were used to develop and evaluate the performance of the proposed method.