22 open source projects by davidstutz

Collection of LaTeX resources and examples.

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.

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

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.

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.

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

JQuery multiselect plugin based on Twitter Bootstrap.

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

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

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

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

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

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

Python tool for obtaining watertight meshes using TSDF fusion.

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

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

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

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].

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

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