David Stutz

bootstrap-multiselect. JQuery multiselect plugin based on Twitter Bootstrap.

latex-resources. Collection of LaTeX resources and examples.

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

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

superpixels-revisited. 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.

mesh-fusion. Python tool for obtaining watertight meshes using TSDF fusion.

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

bootstrap-strength-meter. Password strength meter based on Twitter Bootstrap and Password Score.

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

arxiv-submission-sanitizer-flattener. Simple Python scripts to clean up and flatten ArXiv LaTeX submissions.

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

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

cvpr2018-shape-completion. CVPR 2018 paper "Learning 3D Shape Completion from Laser Scan Data with Weak Supervision".

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

password-score. Password scoring library written in Javascript.

tensorflow-cpp-op-example. Simple example of implementing a new Tensorflow operation and its gradient in C++.

seeds-revised. Implementation of the superpixel algorithm called SEEDS [1].

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

confidence-calibrated-adversarial-training. Implementation of Confidence-Calibrated Adversarial Training (CCAT).

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

extended-berkeley-segmentation-benchmark. Extended version of the Berkeley Segmentation Benchmark [1] used for evaluation in [2].

grosse2009-intrinsic-images. Code from the MIT Intrinsic Images Dataset [1]; Including command line tool for Retinex algorithm.

nyu-depth-v2-tools. Tools used in [2] to pre-process the ground truth segmentations to evaluate superpixel algorithms.

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

hierarchical-graph-based-video-segmentation. 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].

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

sphinx-example. Example and cheat sheet for the Sphinx Python documentation generator.

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

pointnet-auto-encoder. Torch PointNet auto encoder implementation.

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

ijcv2018-improved-shape-completion. ArXiv'18 pre-print "Learning 3D Shape Completion under Weak Supervision".

pytorch-custom-c-cuda-operations. Example of easily implementing custom tensor operations in C and CUDA.

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

cvpr2019-adversarial-robustness. CVPR 2019 paper "Disentangling Adversarial Robustness and Generalization".

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

kohana-hooks. Event module for Kohana.

probabilistic-pca. Python probabilistic PCA (PPCA) implementation.

seminar-convolutional-neural-networks. Seminar paper "Understanding Convolutional Neural Networks".

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

vedaldi2006-siftpp. Fork of SIFT++, a lightweight C++ implementation of the SIFT detector and descriptor.

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

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

icml2020-confidence-calibrated-adversarial-training. ICML'20 paper "Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks".

vlfeat-slic-example. Example of using VLFeat's SLIC implementation from C++.

torch-examples. Collection of Torch examples for deep learning.

mathematical-image-processing. 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.

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

master-thesis-shape-completion. Master thesis "Learning 3D Shape Completion from Bounding Boxes using CAD Shape Priors".

superpixel-benchmark-data. Converted datasets for davidstutz/superpixel-benchmark.

php-simplex. PHP library implementing the simplex algorithm.

jasmine-travis-example. Example for continuous integration with Jasmine, GitHub and Travis CI.

wordpress-iamdavidstutz. Wordpress theme of my personal webpage.

gcpr2015-superpixels. GCPR 2015 paper and poster "Superpixel Segmentation: An Evaluation".

awesome-computer-vision. A curated list of awesome computer vision resources

d3-topological. Topological sort using d3.js.

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

cmsimple-pictures. CMSimple plugin for creating different kinds of sliders and galleries.

davidstutz. Personal README.