My master thesis, written at the Autonomous Vision Group of Max Planck Institute for Intelligent Systems under the supervision of Prof. Andreas Geiger, addresses the problem of 3D shape completion of sparse point clouds under weak supervision. Specifically, based on a learned shape prior it is possible to learn 3D shape completion without access to ground truth shapes, as shown on KITTI. This article briefly introduces the problem and the main contributions and offers the thesis as download.
Part of my master thesis at the Max Planck Institute for Intelligent Systems was an initial proposal — outlining the general idea and the current state-of-the-art. Specifically, I worked on learning 3D shape completion on KITTI using 3D bounding boxes only. In this article, I want to present this proposal.
Weakly-supervised shape completion of cars on KITTI using variational auto-encoders; including two synthetic ShapeNet-based benchmark datasets.
Revised C++ implementations of two popular superpixel algorithms, SEEDS and FH, which are shown to outperform the original implementations.
A comprehensive comparison and evaluation of 28 superpixel algorithms on 5 different datasets; published in CVIU and GCPR.
A comparison of several state-of-the-art superpixel algorithms using an extended version of the Berkeley Segmentation Benchmark.
My bachelor thesis, written at the Computer Vision Group at RWTH Aachen University, discusses superpixel segmentation utilizing depth information. Based on our own implementation of SEEDS [1], we examine the influence of depth information on the performance and compare several variants to other state-of-the-art approaches to superpixel segmentation.
As part of my bachelor thesis at RWTH Aachen University, entitled “Superpixel Segmentation using Depth Information”, I prepared an introductory talk to present my work to the whole Computer Vision Group. This article provides the corresponding slides.
Due to my bachelor thesis at RWTH Aachen University I am currently busy learning everything about superpixel segmentation — the oversegmentation of an image into groups of pixels using low-level features. In this article I want to give a short introduction by presenting my bachelor thesis proposal.