This depth estimation model generates a depth map and a downloadable text file containing depth values for a given input image

Spectral Mapping of Singing Voices: U-Net-Assisted Vocal Segmentation

Automatic localization of optic disc and fovea using only image processing techniques.

Diffusion model designed to generate landscape paintings

U-Net Implementation for Skin Cancer Detection

The repo of the ANN's class final project in NCU (Toruń, Poland). It is an implementation of the paper "U-Net: Convolutional Networks for Biomedical Image Segmentation".

Enhancing glioma tumor segmentation and survival analysis

This project implements semantic image segmentation using two popular convolutional neural network architectures: U-Net and SegNet. Semantic image segmentation involves partitioning an image into multiple segments, each representing a different class.

This is our final project for our software engineering degree. The project is a research revolving generation of multie-scale graph using Graph U-net and diffusion model.

PyTorch implementation of the Dense Inception U-Net

Segmentation of cancerous tumors using Mamba. Code, resources, and paper provided. We manage to make a small (42k param) model that can segment pretty well.

This repository contains the source code for our MM-StrokeNet model.

AI for Eart Observations (AI4EO)

This repository contains the code for Comparing Deep Learning and Classical Computer Vision for Semantic Segmentation: A comprehensive analysis of cutting-edge techniques and algorithms for precise object segmentation in computer vision tasks. This work was done under the Computer Vision course at IIT Jodhpur.

This project utilizes deep learning methodologies to automate the segmentation of a dataset I curated myself, focusing on firearm-specific features within cartridge case images. By employing multi-class semantic segmentation, it aims to enhance firearm identification systems.

Implementation of a U-net complete with efficient attention as well as the latest research findings

The system is designed to segment crops from the background in images collected by Unmanned Aerial Vehicles.

✨ A Img2Img model implemented PyTorch.

Deep Learning Breast MRI Segmentation and Classification

Kurtlab's code for BraTS 2023 submission