There is a huge demand for trying on clothing at home. Recent methods to capture your figure mostly work in a 2d image plane and despite recent improvements of available technology the simulation of clothing is still not satisfactory. Especially the rendering of different clothing sizes is still a major challenge, which is only addressed by COTTON [1]. We propose an improvement to this approach by adding more control over the image generation process. For this we employ a special type of conditional diffusion model, namely ControlNet, and take keypoints of the fashion as conditional input.

In this paper we present a stable-diffusion based zero-shot approach to realistically transform the image of a

human body into a more fit version of that depicted person. Therefore we combine a modified stable diffusion

model with inpainting techniques and incorporated constraints. We introduce a prototype which allows users to

upload a photo and visualize a more fit version of themselves. We evaluated our approach in various experiments

and focused on the applicability and effectiveness of these techniques, with attention to gender-specific results.

This work contributes to the fields of computer vision and generative AI by demonstrating practical applications

and identifying areas for improvement in realistic body transformation visualizations.

The simulation of clothing for a virtual try on is still a challenging task, especially if the customer wants to use state of the art technology. To address this, we employ a 2D plane to process customer images. Specifically, we utilize a neural network, notably an autoencoder, to render so called fashion landmarks. As input we use human keypoints that represent the model poses and our fashion landmarks of the clothing from stock photos to generate fashion landmarks in the desired pose. These can be utilized by additional algorithms to adapt the clothing length or width.

Um den zunehmenden Anforderungen an die Beherrschung digitaler Techniken und an die Fähigkeit zur interdisziplinären Zusammenarbeit an Studierende aller Fach­richtungen zu begegnen wurde das interdisziplinäre Lehrformat Digitalisie­rungs­­kollegs für Studierende entwickelt. Das in vielen Fachbereichen ausbaufähige Angebot von Digitalthemen in der Hoch­schullehre wird hiermit dauerhaft erwei­tert. Ein Digitalisierungskolleg besteht aus einer Vorlesungs­reihe mit an­gren­zen­dem Seminar, in denen Studierende interdisziplinäre Lösungen für Fragen der digitalen Transformation entwickeln. Geleitet werden sie von etablierten Wissen­schaftlerinnen und Wissenschaftlern, aktiv betreut und ausge­staltet von ein bis zwei Coaches. Kernelement sowohl des Kollegs als auch der einzelnen Projekte ist die Interdisziplinarität. Eine*r der beteiligten Projekt­leiter*innen hat einen direkten Bezug zur Technik und kommt aus der Informatik, der Wirtschafts­informatik, der Elektro­technik oder vergleichbaren Disziplinen. Zielgruppe der Projekte sind Studierende verschiedener Disziplinen im Masterstudium oder in den letzten Semestern eines Bachelorstudiums. Durch die Teilnahme er­werben auch Studie­ren­de aus digitali­­sie­rungs­fernen Fächern frühzeitig umfang­reiche IT-Kenntnisse. Als Be­gleiteffekt der um­fang­reichen Vernetzung zwischen den Digi­talisierungs­kollegs (Studierende, Coaches und Projektleitende) entsteht bereits zu Beginn einer wissenschaftlichen Karriere eine große digitale Community. Alle Teil­nehmenden lernen frühzeitig die interdisziplinäre Zusammenarbeit und ver­bessern erheblich ihre Karriere­chancen inner­­halb und außer­halb der Wissenschaft.

EEG classification is a promising approach to facilitate the life of handicapped people and to generate future human-computer-interfaces. In this paper we want to compare the effectiveness of current state of the art deep learning techniques for EEG classification. Therefore, we applied different approaches on various datasets and did a crosscomparison of the results in order to get more knowledge on the generalization capabilities. Additionally, we created a new EEG dataset and made it available for further research.

To provide robots for a wide range of users, there needs to be an easy and intuitive way to program them. This issue is addressed by the robot programming by demonstration or imitation learning paradigm, where the user demonstrates the task to the robot by teleoperation. Although single-shot approaches could save a lot of time and effort, they are still a niche due to some drawbacks, like ambiguities in selecting the relevant features.In this work we try to enhance a single shot programming by demonstration approach on sub-symbolic level by extending it to a multi modal input. While most approaches mainly focus on the trajectories and visual detection of objects, we combine speech and kinestethic teaching in order to resolve ambiguities and to rise the level of transferred information.