distance-transform

Robotics with GPU computing

Euclidean distance & signed distance transform for multi-label 3D anisotropic images using marching parabolas.

Compute the exact Euclidean Distance Transform and Voronoi Diagram for 2D and 3D binary images using the GPU.

A ROS package for converting OccupancyGrid/Costmap2D to 2D distance map.

GPU Accelerated Euclidean Distance Transform

WebGL2 based implementation of distance transform and diffusion curves

A ROS costmap plugin for Euclidean distance map based on OpenCV distance transform function.

An image processing library, including methods of filtering, object detection, noise reduction, etc

Introduces and solves the under-specified Reeds-Shepp problem: find the vehicle orientation that results in the shortest path.

Figma's Liquid Glass effect rebuilt as a real-time WebGL2 renderer. Design glass on any shape or SVG path, then export a copy-paste config. Adds Reach and Soften — two controls Figma doesn't have.

distance transform with Rust ndarray

Testing methods for dequantization of RGBD data

Euclidean distance transform

Matlab image processing programs without using built-in functions.

C++17 reference implementation of camera map-matching localization: rasterize lane/road-boundary perception to distance transforms, score a 3-DOF (x, y, yaw) pose grid against a polyline map, temporally aggregate, and fuse into an SE(3) Kalman filter. Optional CUDA; KITTI eval, benchmarks, and RViz/PNG visualization.

This repository provides an end-to-end implementation of a multi-output U-Net that supports both segmentation and classification, along with a set of distance-based loss functions for improved boundary prediction.

This repository presents the complete code of the paper titled "Learning Free Line Detection in Manuscripts using Distance Transform Graph" published in ICDAR2019.

The MatLab code takes confocal TIFF images of cells as input and plots the distribution of different channels after segmentation of the image into features bases on the type of organelles. For getting the membrane features, distance transform is used to obtain a continuos membrane region.

Topics learned and implemented as part of Computer Vision course