MEGVII Research
MEGVII Research
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)
LGD
Official Implementation of the detection self-distillation framework LGD.
megvii-tsinghua-dl-course
Slides with modifications for a course at Tsinghua University.
ML-GCN
PyTorch implementation of Multi-Label Image Recognition with Graph Convolutional Networks, CVPR 2019.
MOTRv2
[CVPR2023] MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors
PCB
Official code for CVPR 2022 paper "Relieving Long-tailed Instance Segmentation via Pairwise Class Balance".
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)
protoclip
📍 Official pytorch implementation of paper "ProtoCLIP: Prototypical Contrastive Language Image Pretraining" (IEEE TNNLS)