alprnbg

the-algorithm

Source code for Twitter's Recommendation Algorithm

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

google-research

Google Research

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

pytorch-metric-learning

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

moco

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

simclr

SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

lightly

A python library for self-supervised learning on images.

Semantic-Segment-Anything

Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

Monkey

【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models

LLFF

Code release for Local Light Field Fusion at SIGGRAPH 2019

Pointcept

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

moco-v3

PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057

TPVFormer

[CVPR 2023] An academic alternative to Tesla's occupancy network for autonomous driving.

pseudo_lidar

(CVPR 2019) Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving

video_analyst

A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.

MonoScene

[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image

Codes-for-PVKD

Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation (CVPR 2022)

2DPASS

2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds (ECCV 2022) :fire:

PointContrast

Code for paper <PointContrast: Unsupervised Pretraining for 3D Point Cloud Understanding>

EfficientAD

Unofficial implementation of EfficientAD https://arxiv.org/abs/2303.14535

Occupancy-MAE

Official implementation of our TIV'23 paper: Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders

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"

ALSO

ALSO: Automotive Lidar Self-supervision by Occupancy estimation

hierarchicalContrastiveLearning

VA-DepthNet

VA-DepthNet: A Variational Approach to Single Image Depth Prediction

GD-MAE

GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds (CVPR 2023)

voxel-mae

Code for the paper "Masked Autoencoders for Self-Supervised Learning on Automotive Point Clouds"

Unsupervised-Visual-Representation-Learning

Overview of unsupervised visual representation learning (or self-supervised learning, unsupervised pre-training) methods.

MosRep.pytorch

Mosaic Representation Learning for Self-supervised Visual Pre-training (ICLR2023, Spotlight)