Megvii Research

Continuous Innovation Expands Horizons and Broadens the Mind Leveraging Cutting-Edge Technologies to Create Tangible Value

homepage | bilibili | 知乎 | 中文主页

The following list also includes projects from some of Megvii Research's affiliated organizations:

Foundation Model | Base Detection | 3D team | MegEngine

name	description
4K-Face	4K-Face: A Dataset with Huge Scale-variance Faces
AAAI2023-PVD	Official Implementation of PVD:One is All: Bridging the Gap Between Neural Radiance Fields Architectures with Progressive Volume Distillation
ACON	None
AGFlow	Learning Optical Flow with Adaptive Graph Reasoning (AGFlow, AAAI-2022)
AnchorDETR	An official implementation of the Anchor DETR.
AngleNAS	None
Arch-Net	Arch-Net: Model Distillation for Architecture Agnostic Model Deployment
AutoAssign	Pytorch implementation of "AutoAssign: Differentiable Label Assignment for Dense Object Detection"
BBN	The official PyTorch implementation of paper BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition
BEVDepth	Official code for BEVDepth.
BEVStereo	Official code for BEVStereo
BasesHomo	The official PyTorch implementation of the paper "Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection".
BorderDet	BorderDet: Border Feature for Dense Object Detection(ECCV2020 Oral)
CADDM	Official implementation of ID-unaware Deepfake Detection Model
CR-DA-DET	The official PyTorch implementation of paper Exploring Categorical Regularization for Domain Adaptive Object Detection (CR-DA-DET)
CREStereo	Official MegEngine implementation of CREStereo(CVPR 2022 Oral).
CVPR2023-DMVFN	CVPR2023 (highlight) - A Dynamic Multi-Scale Voxel Flow Network for Video Prediction
CVPR2023-UniDistill	UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View
CamLaserCalibraTool	Extrinsic Calibration of a Camera and 2d Laser
CamOdomCalibraTool	The tool to calibrate extrinsic param between camera and wheel
Co-mining	Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection, AAAI 2021.
CoNR	Official implementation of CoNR: Collaborative Neural Rendering using Anime Character Sheets
CrowdDetection	None
D2C-SR	Official MegEngine implementation of ECCV2022 "D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution".
DCLS-SR	Official PyTorch implementation of the paper "Deep Constrained Least Squares for Blind Image Super-Resolution", CVPR 2022.
DPGN	This repository contains the official implementation of DPGN: Distribution Propagation Graph Network for Few-shot Learning.
DVN	None
DeFCN	End-to-End Object Detection with Fully Convolutional Network
DenseTeacher	DenseTeacher: Dense Pseudo-Label for Semi-supervised Object Detection
DetNAS	None
DisAlign	Implementation of "Distribution Alignment: A Unified Framework for Long-tail Visual Recognition"(CVPR 2021)
DiverseBranchBlock	None
Docs	MegEngine Documentations
Documentation	MegEngine Official Documentation
DynamicRouting	Learning Dynamic Routing for Semantic Segmentation
ECCV2022-RIFE	Official MegEngine Implementation of Real-Time Intermediate Flow Estimation for Video Frame Interpolation
ECCV2022-RIFE	ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation
ED-Net	PyTorch implementation of A Lightweight Encoder-Decoder Path for Deep Residual Networks.
End-to-end-ASR-Transformer	An end to end ASR Transformer model training repo
FINet	This is the official MegEngine implementation of FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration, AAAI 2022
FQ-ViT	[IJCAI 2022] FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
FSCE	None
FSSD_OoD_Detection	Feature Space Singularity for Out-of-Distribution Detection. (SafeAI 2021)
FST-Matching	Official implementation of the FST-Matching Model.
FullMatch	Official implementation of FullMatch (CVPR2023)
FunnelAct	None
GFSD	This project provides an implementation for "Generalized Few-Shot Object Detection without Forgetting" (CVPR2021) on PyTorch.
GeneGAN	Pytorch version of GeneGAN
GyroFlow	The official MegEngine implementation of the ICCV 2021 paper: GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning
HDR-Transformer	The official MegEngine implementation of the ECCV 2022 paper: Ghost-free High Dynamic Range Imaging with Context-aware Transformer
HINet	None
HomoGAN	This is the official implementation of HomoGAN, CVPR2022
Hub	基于旷视研究院领先的深度学习算法，提供满足多业务场景的预训练模型
ICCV2019-LearningToPaint	ICCV2019 - Learning to Paint With Model-based Deep Reinforcement Learning
ICD	This is the official implementation of the paper "Instance-conditional Knowledge Distillation for Object Detection", based on MegEngine and Pytorch.
Inference-Demo	推理样例
Iter-E2EDET	Official implementation of the paper "Progressive End-to-End Object Detection in Crowded Scenes"
KD-MVS	Code for ECCV2022 paper 'KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view Stereo'
KPAFlow	PyTorch implementation of KPA-Flow. Learning Optical Flow with Kernel Patch Attention (CVPR-2022)
LBHomo	This is the official PyTorch implementation of Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint, AAAI 2023
LGD	Official Implementation of the detection self-distillation framework LGD.
LLA	Official implementation of our paper "LLA: Loss-aware Label Assignment for Dense Pedestrian Detection" in Pytorch.
LabelEnc	None
MABN	None
MEMD	Megvii Electric Moped Detector (ONNX based inference)
ML-GCN	PyTorch implementation of Multi-Label Image Recognition with Graph Convolutional Networks, CVPR 2019.
MM2022-ViCoPerceptualHeadGeneration	MM2022 Workshop-Perceptual Conversational Head Generation with Regularized Driver and Enhanced Renderer
MOTR	[ECCV2022] MOTR: End-to-End Multiple-Object Tracking with TRansformer
MOTRv2	[CVPR2023] MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors
MSCL	[ECCV2022] Motion Sensitive Contrastive Learning for Self-supervised Video Representation
MSPN	Multi-Stage Pose Network
MegBA	MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment
MegCC	MegCC是一个运行时超轻量，高效，移植简单的深度学习模型编译器
MegCat	A Deep Learning Project about cats.
MegDiffusion	MegEngine implementation of Diffusion Models.
MegEngine-Benchmark	None
MegEngine-DMVFN	None
MegEngine	MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架
MegFlow	Efficient ML solution for long-tailed demands.
MegPeak	None
MegRay	A communication library for deep learning
MegSpot	MegSpot是一款高效、专业、跨平台的图片&视频对比应用
Megvii-BaseDetection	You are welcomed to join us!
MetaPruning	None
Models	采用MegEngine实现的各种主流深度学习模型
NAFNet	The state-of-the-art image restoration model without nonlinear activation functions.
NBNet	NBNet: Noise Basis Learning for Image Denoising with Subspace Projection
NIPS2017-LearningToRunACE	2nd place solution of NIPS2017 LearningToRun Competition.
NeRF	NeRF implementation in MegEngine
NeurIPS2021-ML4CO-KIDA	1st Solution For NeurIPS 2021 Competition on ML4CO Dual Task
OMNet	OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration, ICCV 2021, MegEngine implementation.
OTA	Official implementation of our CVPR2021 paper "OTA: Optimal Transport Assignment for Object Detection" in Pytorch.
OccDepth	Maybe the first academic open work on stereo 3D SSC method with vision-only input.
OdomLaserCalibraTool	Extrinsic Calibration of a Odom and 2d Laser
PCB	Official code for CVPR 2022 paper "Relieving Long-tailed Instance Segmentation via Pairwise Class Balance".
PETR	[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection
PMN	[ACMMM 2022 Best Paper Runner-Up Award] Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling
PMRID	ECCV2020 - Practical Deep Raw Image Denoising on Mobile Devices
Portraits_Correction	None
RG-SENet_SP-SENet	PyTorch implementation of Delving Deep into Spatial Pooling for Squeeze-and-Excitation Networks.
RLNAS	None
RealFlow	The official implementation of the ECCV 2022 Oral paper: RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos
RepLKNet	Official MegEngine implementation of RepLKNet
RepVGG	None
Resource	None
RevCol	Official Code of Paper "Reversible Column Networks"
SMP	None
SOLQ	"SOLQ: Segmenting Objects by Learning Queries", SOLQ is an end-to-end instance segmentation framework with Transformer.
SSQL-ECCV2022	PyTorch implementation of SSQL (Accepted to ECCV2022 oral presentation)
ShuffleNet-Series	None
SimpleDG	This is the training and test code for ECCV2022 workshop NICO challenge
SinglePathOneShot	None
Sobolev_INRs	[ECCV 2022] The official experimental code of "Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives"
Sparsebit	A model compression and acceleration toolbox based on pytorch.
TLC	Test-time Local Converter
TP-LSD	Official implementation of paper "TP-LSD: Tri-points based line segment detector" .
TPS-CVPR2023	None
TransMVSNet	(CVPR 2022) TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers.
Transfer-Learning-Library	Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
TreeEnergyLoss	[CVPR2022] Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation
TreeFilter-Torch	Learnable Tree Filter for Structure-preserving Feature Transform
US3L-CVPR2023	PyTorch implementation of US3L (Accepted to CVPR2023)
WeightNet	None
YOLOF	None
YOLOX	MegEngine implementation of YOLOX
YOLOX	YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
awesome-megengine	Awesome Resources about MegEngine
basecls	A codebase & model zoo for pretrained backbone based on MegEngine.
basecls	A codebase & model zoo for pretrained backbone based on MegEngine.
basecore	basecore is a simple repo that provides deep learning frame for MegEngine.
basedet	An object detection codebase based on MegEngine.
cheat_sheet_for_pytorch_immigrant	一份给从 PyTorch 迁移过来的用户的小抄
cpp_redis	C++11 Lightweight Redis client: async, thread-safe, no dependency, pipelining, multi-platform
cpuinfo	CPU INFOrmation library (x86/x86-64/ARM/ARM64, Linux/Windows/Android/macOS/iOS)
cudnn-frontend	None
cutlass-bak	modified cutlass
cutlass	CUDA Templates for Linear Algebra Subroutines
cv-master-ex	torch version of instant-ngp, image rendering
cvpods	All-in-one Toolbox for Computer Vision Research.
examples	A set of examples around MegEngine
flatbuffers	FlatBuffers: Memory Efficient Serialization Library
gflags	The gflags package contains a C++ library that implements commandline flags processing. It includes built-in support for standard types such as string and the ability to define flags in the source file in which they are used. Online documentation available at:
hpargparse	argparse extension for hpman
hpman	A hyperparameter manager for deep learning experiments.
hpnevergrad	A nevergrad extension for hpman
introduction-neural-3d-reconstruction	Course materials for Introduction to Neural 3D Reconstruction
invis	invisible megengine API
juicefs-python	JuiceFS Python SDK
mdistiller	The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679
megengine-face-recognition	None
megenginelite-rs	None
megfile	Megvii FILE Library - Working with Files in Python
megvii-pku-dl-course	Homepage for the joint course of Megvii Inc. and Peking University on Deep Learning.
megvii-tsinghua-dl-course	Slides with modifications for a course at Tsinghua University.
mgeconvert	MegEngine到其他框架的转换器
midout	Reduce binary size by removing code blocks
mperf-libpfm4	forked from https://sourceforge.net/p/perfmon2/libpfm4/ci/master/tree/
mperf	mperf是一个面向移动/嵌入式平台的算子性能调优工具箱
neural-painter	Paint artistic patterns using random neural network.
oneDNN	oneAPI Deep Neural Network Library (oneDNN)
protoclip	Official pytorch implementation of ProtoCLIP in paper Prototypical Contrastive Language Image Pretraining
pydata-sphinx-theme	Bootstrap-based sphinx theme from the PyData community
pytorch-gym	Implementation of the Deep Deterministic Policy Gradient(DDPG) in bullet Gym using pytorch
revisitAIRL	[ECCV2022] Revisiting the Critical Factors of Augmentation-Invariant Representation Learning
storage	provide Checkpoint for users.
swin-transformer	Swin-Transformer implementation in MegEngine. This is a showcase for training on GPU with less memory by leveraging MegEngine DTR technique.
tf-cpn	Cascade Pyramid Netwrok
tf-tutorials	Tutorials for deep learning course here:
torch2mge	None
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.
xopr	Experimental Operator Library for MegEngine
zipfls	This repo is the official megengine implementation of the ECCV2022 paper: Efficient One Pass Self-distillation with Zipf's Label Smoothing.