Skip to content
@megvii-research

MEGVII Research

Power Human with AI. 持续创新拓展认知边界 非凡科技成就产品价值
README.md

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
ACON CVPR 2021 Activate or Not: Learning Customized Activation
AGFlow Learning Optical Flow with Adaptive Graph Reasoning (AGFlow, AAAI-2022).
AnchorDETR An official implementation of the Anchor DETR.
AngleNAS Angle-based Search Space Shrinking for Neural Architecture Search
Arch-Net Arch-Net: Model Distillation for Architecture Agnostic Model Deployment.
AutoAssign AutoAssign: Differentiable Label Assignment for Dense Object Detection
BBN BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition.
BEVDepth BEVDepth is a new 3D object detector with a trustworthy depth estimation.
BasesHomo "Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection".
BorderDet BorderDet: Border Feature for Dense Object Detection
CR-DA-DET Exploring Categorical Regularization for Domain Adaptive Object Detection (CR-DA-DET).
CREStereo Official MegEngine implementation of CREStereo(CVPR 2022 Oral).
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 CoNR: Collaborative Neural Rendering using Anime Character Sheets.
CrowdDetection Detection in Crowded Scenes: One Proposal, Multiple Predictions
D2C-SR ECCV2022 "D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution".
DCLS-SR "Deep Constrained Least Squares for Blind Image Super-Resolution", CVPR 2022.
DPGN DPGN: Distribution Propagation Graph Network for Few-shot Learning.
DeFCN End-to-End Object Detection with Fully Convolutional Network
DenseTeacher DenseTeacher: Dense Pseudo-Label for Semi-supervised Object Detection
DetNAS DetNAS: Backbone Search for Object Detection
DisAlign Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
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 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 fewshot object detector, described in our CVPR 2021 paper, FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding.
FSSD_OoD_Detection Feature Space Singularity for Out-of-Distribution Detection(SafeAI 2021).
FST-Matching the FST-Matching Model.
FunnelAct Funnel Activation for Visual Recognition
GFSD Generalized Few-Shot Object Detection without Forgetting
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 ECCV 2022 paper: Ghost-free High Dynamic Range Imaging with Context-aware Transformer.
HINet HINet: Half Instance Normalization Network for Image Restoration
HomoGAN [CVPR2022] Unsupervised Homography Estimation with Coplanarity-Aware GAN
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
Iter-E2EDET "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 KPA-Flow. Learning Optical Flow with Kernel Patch Attention (CVPR-2022).
LGD the detection self-distillation framework LGD.
LLA LLA is the first one-stage detector that surpasses two-stage detectors (e.g., Faster R-CNN) on CrowdHuman dataset
LabelEnc LabelEnc: A New Intermediate Supervision Method for Object Detection
MABN Moving Average Batch Normalization
MEMD Megvii Electric Moped Detector (ONNX based inference).
ML-GCN 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
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
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 Megpeak is a tool for testing processor peak computation, now support arm, x86 and GPU driven by OpenCL processor.
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
MetaPruning MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
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 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 Optimal Transport Assignment for Object Detection
OdomLaserCalibraTool Extrinsic Calibration of a Odom and 2d Laser
PCB 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] 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 [CVPR2022] Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer.
RG-SENet_SP-SENet Delving Deep into Spatial Pooling for Squeeze-and-Excitation Networks.
RLNAS Neural Architecture Search with Random Labels(RLNAS)
RealFlow RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos[ECCV 2022 Oral].
RepLKNet Official MegEngine implementation of RepLKNet
RepVGG RepVGG: Making VGG-style ConvNets Great Again (CVPR-2021)
Resource 天元（MegEngine）的周边资源，包括技术文章、活动、最新资讯等。
SOLQ "SOLQ: Segmenting Objects by Learning Queries", SOLQ is an end-to-end instance segmentation framework with Transformer.
SSQL-ECCV2022 SSQL (Accepted to ECCV2022 oral presentation).
ShuffleNet-Series ShuffleNet Series by Megvii Research.
SinglePathOneShot Single Path One-Shot by Megvii Research.
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 pytorch.
TLC Test-time Local Converter.
TP-LSD Official implementation of paper "TP-LSD: Tri-points based line segment detector" .
TransMVSNet (CVPR 2022) TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers.
TreeEnergyLoss [CVPR2022] Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation.
TreeFilter-Torch This project provides a cuda implementation for "Learnable Tree Filter for Structure-preserving Feature Transform" (NeurIPS2019) on PyTorch
WeightNet WeightNet: Revisiting the Design Space of Weight Network
YOLOF You Only Look One-level Feature (YOLOF), CVPR2021
YOLOX MegEngine implementation of YOLOX
YOLOX YOLOX is an anchor-free version of YOLO, with a simpler design but better performance! It aims to bridge the gap between research and industrial communities.
basecls A codebase & model zoo for pretrained backbone based on MegEngine.
basecore basecore is a simple repo that provides deep learning frame for MegEngine.
cutlass-bak modified cutlass
cutlass CUDA Templates for Linear Algebra Subroutines
cv-master-ex torch version of instant-ngp, image rendering.
cvpods The aim of cvpods is to achieve efficient experiments management and smooth tasks-switching
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.
juicefs-python JuiceFS Python SDK.
mdistiller [CVPR2022] Decoupled Knowledge Distillation
megengine-face-recognition CV Master , bilibili, megstudio
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
neural-painter Paint artistic patterns using random neural network.
protoclip ProtoCLIP in paper Prototypical Contrastive Language Image Pretraining.
pytorch-gym Deep Deterministic Policy Gradient(DDPG) in bullet Gym using pytorch.
revisitAIRL [ECCV2022] Revisiting the Critical Factors of Augmentation-Invariant Representation Learning
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.
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.
zipfls the ECCV2022 paper: Efficient One Pass Self-distillation with Zipf's Label Smoothing.

If you have questions about this page, please contact zhanghuiying@megvii.com or huangzhewei@megvii.com.

Pinned

  1. ECCV2022-RIFE Public

    ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation

    Python 3.1k 345

  2. ICCV2019-LearningToPaint Public

    ICCV2019 - Learning to Paint With Model-based Deep Reinforcement Learning

    Python 2.2k 313

  3. BBN Public

    The official PyTorch implementation of paper BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition

    Python 627 92

  4. NAFNet Public

    The state-of-the-art image restoration model without nonlinear activation functions.

    Python 1.2k 132

  5. CoNR Public

    Official implementation of CoNR: Collaborative Neural Rendering using Anime Character Sheets

    Jupyter Notebook 673 67

  6. mdistiller Public

    The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679

    Python 502 84

Repositories

  • SSQL-ECCV2022 Public

    PyTorch implementation of SSQL (Accepted to ECCV2022 oral presentation)

    Python 64 Apache-2.0 4 0 0 Updated Mar 15, 2023
  • US3L-CVPR2023 Public

    PyTorch implementation of US3L (Accepted to CVPR2023)

    Python 10 Apache-2.0 0 0 0 Updated Mar 13, 2023
  • megfile Public

    Megvii FILE Library - Working with Files in Python

    Python 77 Apache-2.0 11 9 1 Updated Mar 13, 2023
  • SMP Public
    0 0 0 0 Updated Mar 13, 2023
  • CADDM Public

    Official implementation of ID-unaware Deepfake Detection Model

    C++ 4 Apache-2.0 0 0 0 Updated Mar 13, 2023
  • CoNR Public

    Official implementation of CoNR: Collaborative Neural Rendering using Anime Character Sheets

    Jupyter Notebook 673 MIT 67 0 0 Updated Mar 11, 2023
  • RevCol Public

    Official Code of Paper "Reversible Column Networks"

    Python 113 Apache-2.0 3 1 0 Updated Mar 10, 2023
  • Sparsebit Public

    A model compression and acceleration toolbox based on pytorch.

    Python 182 Apache-2.0 25 4 9 Updated Mar 9, 2023
  • PETR Public

    [ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection

    Python 467 70 32 0 Updated Mar 9, 2023
  • AAAI2023-PVD Public

    Official Implementation of PVD:One is All: Bridging the Gap Between Neural Radiance Fields Architectures with Progressive Volume Distillation

    Python 86 MIT 3 1 0 Updated Mar 8, 2023
View all repositories