Name: Guofeng Mei
Type: User
Company: Fondazione Bruno Kessler
Bio: Guofeng Mei received an M.S. degree in computational mathematics at Wuhan University, Wuhan. He is currently a Ph.D. student at University of Technology Sydney.
Twitter: CvGfmei
Location: Trento
Blog: https://gfmei.github.io
Guofeng Mei's Projects
List of Algorithms
Image autosegmentation with graph cuts, alpha expansion, and histogram of colors
Unsupervised Point Cloud Pre-training via Contrasting and Clustering
Official codes for ConMIM (ICLR 2023)
keras-Dual Attention Network for Scene Segmentation
My Keras implementation of the Deep Semantic Similarity Model (DSSM)/Convolutional Latent Semantic Model (CLSM) described here: http://research.microsoft.com/pubs/226585/cikm2014_cdssm_final.pdf.
[CVPR 2022] Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization
Python implementation of Efficient Graph-Based Image Segmentation
Graph Machine Learning course, Xavier Bresson, 2023
π₯GrowSP in PyTorch (CVPR 2023)
εζ‘₯ι
ζ
[IEEE RAL 2022] IMFNet: Interpretable Multimodal Fusion for Point Cloud Registration
Implementing a ChatGPT-like LLM from scratch, step by step
a Pytorch library for multi-view 3D understanding and generation
Numpy implementation of Hilbert curves in arbitrary dimensions
Overlap-guided Coarse-to-fine Correspondence prediction for Point Cloud Registration
Overlap-guided Gaussian Mixture Models for Point Cloud Registration
Open3DIS: Open-vocabulary 3D Instance Segmentation with 2D Mask Guidance (CVPR 2024)
image process
RPM-Net: Robust Point Matching using Learned Features (CVPR2020)
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Segmentator for clustering on meshes or pointclouds
[CVPR' 22 ORAL] SIGMA: Semantic-complete Graph Matching for Domain Adaptative Object Detection
Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding