RGB-T Fusion, RGB-T SOD, RGB-T Vehicle Detection, RGB-T Crowd Counting, RGB-T Pedestrian Detection, RGB-T Semantic Segmeantaion, RGB-T Tracking

This repository is about the work "Dual-Perspective Alignment Learning for Multimodal Remote Sensing Object Detection" in IEEE TGRS 2025.

[TPAMI 2025, Highly Cited Paper] Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection

Baseline Code for CVPR 2023 paper. "Multispectral Video Semantic Segmentation: A Benchmark Dataset and Baseline".

Dataset & Code for ACM Multimedia 2023 paper. "SemanticRT: A Large-Scale Dataset and Method for Robust Semantic Segmentation in Multispectral Images".

A selection of RGB-T object tracking papers and their performance on various benchmarks.

Simple and Efficient Adaptation of Visual Geometric Transformers for RGB+Thermal 3D Reconstruction

DCFNet: Dense Complementary Fusion for RGB-Thermal Urban Scene Perception published in the 18th International Symposium on Neural Networks (ISNN 2024)

Python tool for precise thermal to RGB image alignment using feature matching and homography. Ideal for multispectral fusion and computer vision.

Implementation of RTFNet: RGB-Thermal Fusion Network for Semantic Segmentation of Urban Scenes (IEEE RAL) for RGB-D dataset using PyTorch

Pixel x4 is a image super-resolution deep learning algorithm. It uses both the deep convolutional GANs for generating realistic images and the distance based loss function for creating visually similar images.