-
北京理工大学 Beijing Institute of Technology
- 中国北京 Beijing, China
-
12:19
(UTC +08:00)
Lists (3)
Sort Name ascending (A-Z)
Starred repositories
Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.
[CVPR 2025] MINIMA: Modality Invariant Image Matching
GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)
Experimental code to read/write NumPy .NPY files in MATLAB
Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining
Swin Unet V2 is a modified version of Swin Unet based on Swin Transfomer V2.
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
[ECCVW 2022] The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"
XoFTR is a cross-modal cross-view method for local feature matching between thermal infrared (TIR) and visible images.
An updated and practical version of MS-HLMO
A general cross-modal/source image matching algorithm
A feature-based registration algorithm for multi-source images
Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022
D2-Net: A Trainable CNN for Joint Description and Detection of Local Features
Code of single-view depth prediction algorithm on Internet Photos described in "MegaDepth: Learning Single-View Depth Prediction from Internet Photos, Z. Li and N. Snavely, CVPR 2018".
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
Superpoint Implemented in PyTorch: https://arxiv.org/abs/1712.07629