gfmei

ogmm

Overlap-guided Gaussian Mixture Models for Point Cloud Registration

SoftClu

Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding

GeoZe

conclu

Unsupervised Point Cloud Pre-training via Contrasting and Clustering

GML2023

Graph Machine Learning course, Xavier Bresson, 2023

IMFNet

[IEEE RAL 2022] IMFNet: Interpretable Multimodal Fusion for Point Cloud Registration

LLMs-from-scratch

Implementing a ChatGPT-like LLM from scratch, step by step

segment-anything

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.

autosegment-graphcuts

Image autosegmentation with graph cuts, alpha expansion, and histogram of colors

clurender

ConMIM

Official codes for ConMIM (ICLR 2023)

DANet-keras

keras-Dual Attention Network for Scene Segmentation

Deep-Semantic-Similarity-Model

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.

gfmei.github.io

CUDA-code

Deep-Semantic-Feature-Matching

deep-spectral-segmentation

[CVPR 2022] Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization

felzenszwalb_segmentation

Python implementation of Efficient Graph-Based Image Segmentation

GrowSP

🔥GrowSP in PyTorch (CVPR 2023)

IELTS

剑桥雅思

Normalized-Cuts-and-Image-Segmentation-Matlab-Implementation

OCFNet

Overlap-guided Coarse-to-fine Correspondence prediction for Point Cloud Registration

python

image process

RPMNet

RPM-Net: Robust Point Matching using Learned Features (CVPR2020)

SIGMA

[CVPR' 22 ORAL] SIGMA: Semantic-complete Graph Matching for Domain Adaptative Object Detection

Stratified-Transformer

Stratified Transformer for 3D Point Cloud Segmentation (CVPR 2022)

structure_iden_cs

superpixel-benchmark

An extensive evaluation and comparison of 28 state-of-the-art superpixel algorithms on 5 datasets.