David Stutz

JQuery multiselect plugin based on Twitter Bootstrap.

Collection of LaTeX resources and examples.

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

C++ implementation for computing occupancy grids and signed distance functions (SDFs) from watertight meshes.

Library containing 7 state-of-the-art superpixel algorithms with a total of 9 implementations used for evaluation purposes in [1] utilizing an extended version of the Berkeley Segmentation Benchmark.

Python tool for obtaining watertight meshes using TSDF fusion.

Blender/bpy utilities for paper-ready visualizations of meshes, point clouds and occupancy grids.

Password strength meter based on Twitter Bootstrap and Password Score.

Some tools and examples for pyCaffe including LMDB I/O, custom Python layers and monitoring training error and loss.

Simple Python scripts to clean up and flatten ArXiv LaTeX submissions.

PyTorch code corresponding to my blog series on adversarial examples and (confidence-calibrated) adversarial training.

A two layer perceptron implemented in MatLab to recognize handwritten digits based on the MNIST dataset.

CVPR 2018 paper "Learning 3D Shape Completion from Laser Scan Data with Weak Supervision".

Efficient C++ implementation of mesh-to-mesh and mesh-to-point distance.

Password scoring library written in Javascript.

Simple example of implementing a new Tensorflow operation and its gradient in C++.

Implementation of the superpixel algorithm called SEEDS [1].

Implementation of efficient graph-based image segmentation as proposed by Felzenswalb and Huttenlocher [1] that can be used to generate oversegmentations.

Implementation of Confidence-Calibrated Adversarial Training (CCAT).

CVPR'19 experiments with (on-manifold) adversarial examples.

Extended version of the Berkeley Segmentation Benchmark [1] used for evaluation in [2].

Code from the MIT Intrinsic Images Dataset [1]; Including command line tool for Retinex algorithm.

Implementation of the hierarchical graph-based video segmentation algorithm proposed by Grundmann et al. [1] based on the image segmentation algorithm by Felzenswalb and Huttenlocher [2].

An example of using Google Mock inspired by Martin Fowler's "Mocks Aren't Stubs".

Tools used in [2] to pre-process the ground truth segmentations to evaluate superpixel algorithms.

CVPR'18 implementation of (deterministic) amortized maximum likelihood (AML) for weakly-supervised shape completion.

Example and cheat sheet for the Sphinx Python documentation generator.

Fork and OpenCV wrapper of the optical flow I/O and visualization code provided as part of the Sintel dataset [1].

Torch PointNet auto encoder implementation.

Minimal but elegant file upload button for Twitter Bootstrap and IE 7/8/9 support.

ArXiv'18 pre-print "Learning 3D Shape Completion under Weak Supervision".

Example of easily implementing custom tensor operations in C and CUDA.

Implementation of average- and worst-case robust flatness measures for adversarial training.

CVPR 2019 paper "Disentangling Adversarial Robustness and Generalization".

Event module for Kohana.

Python probabilistic PCA (PPCA) implementation.

Seminar paper "Understanding Convolutional Neural Networks".

This is a quick patch for compiling OpenCV 2.4.x with CUDA 9.

Implementation of the iPiano algorithm for non-convex and non-smooth optimization as described in [1].

ArXiv'18 implementation of amortized maximum likelihood (AML) for high-quality, weakly-supervised shape completion.

Fork of SIFT++, a lightweight C++ implementation of the SIFT detector and descriptor.

Bachelor thesis "Superpixel Segmentation using Depth Information", including a thorough comparison of several state-of-the-art superpixel algorithms.

ICML'20 paper "Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks".

Example of using VLFeat's SLIC implementation from C++.

Collection of Torch examples for deep learning.

Implementation of robust quantization, weight clipping and random bit error training to improve robustness against bit errors in quantized weights.

Implementations and examples of basic mathematical image processing algorithms. Based on the lectures "Mathematical Foundations of Image Processing" and "Variational Methods in Image Processing" by Prof. Berkels.

Master thesis "Learning 3D Shape Completion from Bounding Boxes using CAD Shape Priors".

Converted datasets for davidstutz/superpixel-benchmark.

ICCV'21 paper "Relating Adversarially Robust Generalization to Flat Minima".

Wordpress theme of my personal webpage.

Fork of the Light Random Spray Retinex Algorithm as discussed in [1].

Lightweight jQuery plugin to display algorithms similar to LaTeX pseudocode and algorithm packages.

Example for continuous integration with Jasmine, GitHub and Travis CI.

Demonstration of common matrix decompositions in PHP.

PHP library implementing the simplex algorithm.

A curated list of awesome computer vision resources

MLSys'21 paper "Bit Error Robustness for Energy-Efficient DNN Accelerators".

GCPR 2015 paper and poster "Superpixel Segmentation: An Evaluation".

Fork of the Retinex PDE algorithm as desribed in [1].

Fork of Tiny CNN, a C++11 convolutional neural network library.

Topological sort using d3.js.

Small demo application for calculating candidate keys of a given relational database schema.

Seminar paper "Introduction to Neural Networks".

Interactive compariosn of superpixel algorithms as presented in the bachelor thesis "Superpixel Segmentation using Depth Information" [1].

Interactive plots of results from the superpixel benchmark davidstutz/superpixel-benchmark using NVD3.

CMSimple plugin for creating different kinds of sliders and galleries.

Navigation generation module for Kohana.

PHP Library including several common matrix decompositions: LU, QR and Cholesky.

Seminar paper "Neural Codes for Image Retreival".

Kohana authentication module based on Kohana's ORM and Database module.

MEX wrapper for Ali Rahimi's multi-label connected components implementation in C++.

BBClone plugin for CMSimple.

PyTorch code corresponding to my blog series on bit error robustness and bit error training.

Personal README.

CMSimple theme of my personal webpage.

CMSimple plugin for managing and publishing news.

RWTH Aachen University Proseminar 2012 Chair for Data Management and Data Exploration: Dart - A Brief Introduction

Project of "Social Network Analysis" MOOC by the University of Michigan on analyzing StackExchange sites.

Seminar paper "iPiano: Inertial Proximal Algorithm for Non-Convex Optimization".

Wordpress GitHub plugin.

Kohana form creation module based on ORM models.

Kohana Access Control List implementation based on Kohana's Red module.

Naive plugin to easily create labels and references as in LaTeX/BibTeX based on davidstutz/jquery-references.

A simple CMSimple theme based on Twitter Bootstrap.

CMSimple elFinder filebrowser.

CMSimple plugin for creating youtube video galleries.

Simple media/assets module for Kohana.

Naive jQuery plugin to allow referencing figures, listings, algorithms and references in a BibTex-like style.

Main repository for The Video Segmentation Project

Code repository of all tutorials found at http://learnopengl.com

Marching cubes (and related tools) for Python

CADL course project: different architectures implemented in TensorFlow and tested on MNIST.

Blue is a user configuration module based on Kohana's Red module.

Yellow is a logging module for the Kohana Green module based on Green and Red.

MATLAB Toolbox for the LabelMe Image Database

Google Test

Spelling, grammar and style checking on LaTeX documents

Fast, differentiable sorting and ranking in PyTorch

Volumetric nearest neighbor upsampling for Torch based on kmul00/torch-vol.

Batch Normalization for OctNets.

RWTH Aachen University Proseminar 2012 Chair for Data Management and Data Exploration: Dart - A Brief Introduction - Sample application "Contacts".

CVIU 2018 paper "Superpixels: An Evaluation of the State-of-the-Art" - https://arxiv.org/abs/1612.01601.

CMSimple elRTE WYSIWYG editor.

Wordpress plugin for timeline-like user biography - still in development!

Example of Google Fruit for dependency injection based on Martin Fowler's "Inversion of Control Containers and the Dependency Injection Pattern".

Kohana module to read iCal files, based on fangel/SG-iCalendar.

A demo application based on Kohana showing the usage of several modules.

Data used for examples in daidstutz/caffe-tools.

Provides color names and HTML/RGB mappings in various output formats.

Fruit, a dependency injection framework for C++

C++ implementation of the Google logging module

C++ Random Forest Library

No description.

C++ implementation of the Local Binary Pattern texture descriptors. This class integrates with OpenCV and FFTW3 to bring a complete and fast implementation of the popular descriptors: LBP u2, ri, riu2 & hf. The routines for calculating these descriptors are inspired by the Matlab code of the original authors.

Official source code for TLD

The kohana-modules.com module "database".

Fork of the "Color Sparrow" color constancy algorithm described in [1].