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
Languages
Top Repositories
The state-of-the-art image restoration model without nonlinear activation functions.
PyTorch implementation of Multi-Label Image Recognition with Graph Convolutional Networks, CVPR 2019.
[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
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
A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.
[ECCV 2024] HiDiffusion: Increases the resolution and speed of your diffusion model by only adding a single line of code!
Repositories
92The state-of-the-art image restoration model without nonlinear activation functions.
No description provided.
[ECCV2022] MOTR: End-to-End Multiple-Object Tracking with TRansformer
[IROS2025]This is the offical implementation of the paper "MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving"
Official MegEngine implementation of CREStereo(CVPR 2022 Oral).
Slides with modifications for a course at Tsinghua University.
No description provided.
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
[AAAI2024] Far3D: Expanding the Horizon for Surround-view 3D Object Detection
A model compression and acceleration toolbox based on pytorch.
[IJCAI 2022] FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
Maybe the first academic open work on stereo 3D SSC method with vision-only input.
[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)
Megvii FILE Library - Working with Files in Python same as the standard library
Common Formats. Uncommon Speed.
Test-time Local Converter
The official PyTorch implementation of paper BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition
No description provided.
[CVPR2023] MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors
[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.
No description provided.
[ECCV 2024] HiDiffusion: Increases the resolution and speed of your diffusion model by only adding a single line of code!
An official implementation of the Anchor DETR.
[SafeAI'21] Feature Space Singularity for Out-of-Distribution Detection.
The official implementation of the ECCV 2022 Oral paper: RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos
PyTorch implementation of Multi-Label Image Recognition with Graph Convolutional Networks, CVPR 2019.
IJCAI2023 - Collaborative Neural Rendering using Anime Character Sheets
The official MegEngine implementation of the ECCV 2022 paper: Ghost-free High Dynamic Range Imaging with Context-aware Transformer
No description provided.