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

China

Pinned Repositories

BBN
The official PyTorch implementation of paper BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition
Language:Python657 12 29101
CREStereo
Official MegEngine implementation of CREStereo(CVPR 2022 Oral).
Language:Python454 13 5556
HiDiffusion
Language:Jupyter Notebook598 6 2436
IJCAI2023-CoNR
IJCAI2023 - Collaborative Neural Rendering using Anime Character Sheets
Language:Jupyter Notebook787 19 1175
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
Language:Python753 8 65115
ML-GCN
PyTorch implementation of Multi-Label Image Recognition with Graph Convolutional Networks, CVPR 2019.
Language:Python1.4k 28 0345
NAFNet
The state-of-the-art image restoration model without nonlinear activation functions.
Language:Python2k 21 138251
PETR
[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
Language:Python800 15 154121
Sparsebit
A model compression and acceleration toolbox based on pytorch.
Language:Python321 12 3039
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.
Language:Python814 29 131175

MEGVII Research's Repositories

megvii-research/NAFNet
The state-of-the-art image restoration model without nonlinear activation functions.
Language:Python2k 21 138251
megvii-research/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.
Language:Python814 29 131175
megvii-research/PETR
[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
Language:Python800 15 154121
megvii-research/IJCAI2023-CoNR
IJCAI2023 - Collaborative Neural Rendering using Anime Character Sheets
Language:Jupyter Notebook787 19 1175
megvii-research/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
Language:Python753 8 65115
megvii-research/HiDiffusion
Language:Jupyter Notebook598 6 2436
megvii-research/MOTR
[ECCV2022] MOTR: End-to-End Multiple-Object Tracking with TRansformer
Language:Python560 13 7889
megvii-research/Sparsebit
A model compression and acceleration toolbox based on pytorch.
Language:Python321 12 3039
megvii-research/FQ-ViT
[IJCAI 2022] FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
Language:Python288 5 4447
megvii-research/RevCol
Official Code of Paper "Reversible Column Networks" "RevColv2"
Language:Python245 12 1810
megvii-research/TLC
Test-time Local Converter
Language:Python218 8 2710
megvii-research/DCLS-SR
Official PyTorch implementation of the paper "Deep Constrained Least Squares for Blind Image Super-Resolution", CVPR 2022.
Language:Python216 9 5818
megvii-research/AAAI2023-PVD
Official Implementation of PVD and PVDAL: http://sk-fun.fun/PVD-AL/
Language:Python183 9 55
megvii-research/CADDM
Official implementation of ID-unaware Deepfake Detection Model
Language:C++123 6 4518
megvii-research/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)
Language:Python120 9 1914
megvii-research/Far3D
[AAAI2024] Far3D: Expanding the Horizon for Surround-view 3D Object Detection
Language:Jupyter Notebook114 4 275
megvii-research/megfile
Megvii FILE Library - Working with Files in Python same as the standard library
Language:Python110 3 4315
megvii-research/CVPR2023-UniDistill
CVPR2023 (highlight) - UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View
Language:Python99 8 1310
megvii-research/expman
Language:Shell62 5 12
megvii-research/protoclip
📍 Official pytorch implementation of paper "ProtoCLIP: Prototypical Contrastive Language Image Pretraining" (IEEE TNNLS)
Language:Python44 8 00
megvii-research/FullMatch
Official implementation of FullMatch (CVPR2023)
Language:Python39 7 32
megvii-research/TPS-CVPR2023
Language:Python38 7 20
megvii-research/IntLLaMA
IntLLaMA: A fast and light quantization solution for LLaMA
Language:Python21 4 00
megvii-research/MegFaceAnimate
Language:Python213
megvii-research/Occ2net
Language:Jupyter Notebook13 3 21
megvii-research/SimpleDG
This is the training and test code for ECCV2022 workshop NICO challenge
Language:Python7 4 0
megvii-research/.github
2 5 01
megvii-research/DRConv
Language:Python1 3 01
megvii-research/SYP
0 5 00
megvii-research/SCSC
Language:Python3 01