MEGVII Research

ICCV2019-LearningToPaint

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

mdistiller

The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf

BBN

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

MOTR

[ECCV2022] MOTR: End-to-End Multiple-Object Tracking with TRansformer

megvii-pku-dl-course

Homepage for the joint course of Megvii Inc. and Peking University on Deep Learning.

AnchorDETR

An official implementation of the Anchor DETR.

TransMVSNet

(CVPR 2022) TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers.

PMN

[TPAMI 2023 / ACMMM 2022 Best Paper Runner-Up Award] Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling (a Data Perspective)

TreeEnergyLoss

[CVPR2022] Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation

hpman

A hyperparameter manager for deep learning experiments.

RealFlow

The official implementation of the ECCV 2022 Oral paper: RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos

HDR-Transformer

The official MegEngine implementation of the ECCV 2022 paper: Ghost-free High Dynamic Range Imaging with Context-aware Transformer

megvii-tsinghua-dl-course

Slides with modifications for a course at Tsinghua University.

BasesHomo

The official PyTorch implementation of the paper "Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection".

MM2022-ViCoPerceptualHeadGeneration

MM2022 Workshop-Perceptual Conversational Head Generation with Regularized Driver and Enhanced Renderer

protoclip

📍 Official pytorch implementation of paper "ProtoCLIP: Prototypical Contrastive Language Image Pretraining" (IEEE TNNLS)

D2C-SR

Official MegEngine implementation of ECCV2022 "D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution".

KD-MVS

Code for ECCV2022 paper 'KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view Stereo'

AGFlow

Learning Optical Flow with Adaptive Graph Reasoning (AGFlow, AAAI-2022)

HomoGAN

This is the official implementation of HomoGAN, CVPR2022

KPAFlow

PyTorch implementation of KPA-Flow. Learning Optical Flow with Kernel Patch Attention (CVPR-2022)

FST-Matching

Official implementation of the FST-Matching Model.

Portraits_Correction

Sobolev_INRs

[ECCV 2022] The official experimental code of "Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives"

basedet

An object detection codebase based on MegEngine.

zipfls

This repo is the official megengine implementation of the ECCV2022 paper: Efficient One Pass Self-distillation with Zipf's Label Smoothing.

hpargparse

argparse extension for hpman

MSCL

[ECCV2022] Motion Sensitive Contrastive Learning for Self-supervised Video Representation

revisitAIRL

[ECCV2022] Revisiting the Critical Factors of Augmentation-Invariant Representation Learning

basecore

basecore is a simple repo that provides deep learning frame for MegEngine.