Sebastian Pasewaldt

Sebastian Pasewaldt
Hasso Plattner Institute · Research Group Computer Graphics Systems

M.Sc.

About

49
Publications
16,702
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
223
Citations

Publications

Publications (49)
Preprint
Full-text available
Image acquisition in low-light conditions suffers from poor quality and significant degradation in visual aesthetics. This affects the visual perception of the acquired image and the performance of various computer vision and image processing algorithms applied after acquisition. Especially for videos, the additional temporal domain makes it more c...
Conference Paper
Full-text available
We present StyleTune, a mobile app for interactive style transfer enhancement that enables global and spatial control over stroke elements and can generate high fidelity outputs. The app uses adjustable neural style transfer (NST) networks to enable art-direction of stroke size and orientation in the output image. The implemented approach enables c...
Conference Paper
Full-text available
We present MotionViz, an interactive iOS mobile app that enables users to amplify motion and dynamics in videos. MotionViz implements novel augmented reality and expressive rendering techniques in an end-to-end processing pipeline: multi-dimensional video data is captured, analyzed, and processed to render animated graphical elements that help expr...
Conference Paper
Full-text available
Taking selfies is a common practice for smartphone users. Simultaneously capturing oneself and the desired background is not a trivial task, because it is often not possible to get a good view of both. Moreover, users often loose attention of their surroundings, thus taking a selfie also showed to lead to serious injuries. To ease the process of ca...
Presentation
Full-text available
Presentation of research paper "Service-based Processing of Gigapixel Images" presented at 29. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG 2021).
Presentation
Full-text available
Presentation of research paper "Interactive Photo Editing on Smartphones via Intrinsic Decomposition" presented at 42nd Annual Conference of the European Association for Computer Graphics (Eurographics’2021).
Presentation
Full-text available
Presentation of education paper "Teaching Data-driven Video Processing via Crowdsourced Data Collection" presented at 42nd Annual Conference of the European Association for Computer Graphics (Eurographics’2021).
Conference Paper
Full-text available
This paper presents the concept and experience of teaching an undergraduate course on data-driven image and video processing. When designing visual effects that make use of Machine Learning (ML) models for image-based analysis or processing, the availability of training data typically represents a key limitation when it comes to feasibility and eff...
Conference Paper
Full-text available
This paper describes an approach for using the Unity game engine for image processing by integrating a custom GPU-based image processor. It describes different application levels and integration approaches for extending the Unity game engine. It further documents the respective software components and implementation details required, and demonstrat...
Poster
Full-text available
This paper describes an approach for using the Unity game engine for image processing by integrating a custom GPU-based image processor. It describes different application levels and integration approaches for extending the Unity game engine. It further documents the respective software components and implementation details required, and demonstrat...
Presentation
Full-text available
Presentation of the research paper "Integration of Image Processing Techniques into the Unity Game Engine" at the 1st International Conference on Image Processing and Vision Engineering (IMPROVE 2021).
Article
Full-text available
Intrinsic decomposition refers to the problem of estimating scene characteristics, such as albedo and shading, when one view or multiple views of a scene are provided. The inverse problem setting, where multiple unknowns are solved given a single known pixel-value, is highly under-constrained. When provided with correlating image and depth data, in...
Conference Paper
Full-text available
With the ongoing improvement of digital cameras and smartphones, more and more people can acquire high-resolution digital images. Due to their size and high performance requirements, such Gigapixel Images (GPIs) areoften challenging to process and explore compared to conventional low resolution images. To address this problem,this paper presents a...
Conference Paper
Full-text available
With the ongoing improvement of digital cameras and smartphones, more and more people can acquire high- resolution digital images. Due to their size and high performance requirements, such Gigapixel Images (GPIs) are often challenging to process and explore compared to conventional low resolution images. To address this problem, this paper presents...
Article
Full-text available
Mobile expressive rendering gained increasing popularity among users seeking casual creativity by image stylization and supports the development of mobile artists as a new user group. In particular, neural style transfer has advanced as a core technology to emulate characteristics of manifold artistic styles. However, when it comes to creative expr...
Conference Paper
Full-text available
A convenient post-production video processing approach is to apply image filters on a per-frame basis. This allows the flexibility of extending image filters—originally designed for still images—to videos. However, per-image filtering may lead to temporal inconsistencies perceived as unpleasant flickering artifacts, which is also the case for dense...
Presentation
Full-text available
Presentation of Research Paper "Performance Evaluation and Comparison of Service-based Image Processing based on Software Rendering"
Conference Paper
Full-text available
This paper presents an approach and performance evaluation of performing service-based image processing using software rendering implemented using Mesa3D. Due to recent advances in cloud computing technology (with respect to both, hardware and software) as well as increased demands of image processing and analysis techniques, often within an eco-sy...
Conference Paper
Full-text available
This paper presents a GPU-based approach to color quantization by mapping of arbitrary color palettes to input images using Look-up Tables (LUT). For it, different types of LUT, their GPU-based generation, representation, and respective mapping implementations are described and their run-time performance evaluated and compared.
Poster
Full-text available
3D geovirtual environments can be used as scenery for visualizing thematic data encoded as patterns. For rendering purposes, these patterns can be represented as image-based or procedural textures. The resulting quality of image-based textures is subject to resolution and ltering artifacts-in contrast to procedural textures. However, challenges in...
Conference Paper
Full-text available
3D geovirtual environments, such as virtual 3D city and landscape models, can be used as scenery for visualizing thematic data. which can be communicated using suitable color mappings or hatch patterns. For rendering purposes, these hatches patterns can be represented as image-based or procedural textures. The resulting quality of image-based textu...
Conference Paper
Full-text available
Mobile expressive rendering gained increasing popularity amongst users seeking casual creativity by image stylization and supports the development of mobile artists as a new user group. In particular, the neural style transfer has advanced as a core technology to emulate characteristics of manifold artistic styles and media without deep prior knowl...
Poster
Full-text available
This work presents enhancements to state-of-the-art adaptive neural style transfer techniques, thereby providing a generalized user interface with creativity tool support for lower-level local control to facilitate the demanding interactive editing on mobile devices. The approaches are implemented in a mobile app that is designed for orchestration...
Conference Paper
Full-text available
We present MaeSTrO, a mobile app for image stylization that empowers users to direct, edit and perform a neural style transfer with creative control. The app uses iterative style transfer, multi-style generative and adaptive networks to compute and apply flexible yet comprehensive style models of arbitrary images at run-time. Compared to other mobi...
Conference Paper
Full-text available
In this paper we present a concept of a research course that teaches students in image processing as a building block of mobile applications. Our goal with this course is to teach theoretical foundations, practical skills in software development as well as scientific working principles to qualify graduates to start as fully-valued software develope...
Presentation
Full-text available
Presentation of Education Paper "Teaching Image-Processing Programming for Mobile Devices"
Conference Paper
Full-text available
This work presents advances in the design and implementation of Pictory, an iOS app for artistic neural style transfer and interactive image editing using the CoreML and Metal APIs. Pictory combines the benefits of neural style transfer, e.g., high degree of abstraction on a global scale, with the interactivity of GPU-accelerated stateof-the-art im...
Conference Paper
Full-text available
Photo filtering apps successfully deliver image-based stylization techniques to a broad audience, in particular in the ubiquitous domain (e.g., smartphones, tablet computers). Interacting with these inherently complex techniques has so far mostly been approached in two different ways: (1) by exposing many (technical) parameters to the user, resulti...
Conference Paper
Full-text available
With the continuous development of mobile graphics hardware, interactive high-quality image stylization based on nonlinear filtering is becoming feasible and increasingly used in casual creativity apps. However, these apps often only serve high-level controls to parameterize image filters and generally lack support for low-level (artistic) control,...
Conference Paper
Full-text available
BeCasso is a mobile app that enables users to transform photos into high-quality, high-resolution non-photorealistic renditions, such as oil and watercolor paintings, cartoons, and colored pencil drawings, which are inspired by real-world paintings or drawing techniques. In contrast to neuronal network and physically-based approaches, the app emplo...
Poster
Full-text available
This work presents an interactive mobile implementation of a filter that transforms images into an oil paint look. At this, a multi-scale approach that processes image pyramids is introduced that uses flow-based joint bilateral upsampling to achieve deliberate levels of abstraction at multiple scales and interactive frame rates. The approach facili...
Poster
Full-text available
Image stylization enjoys a growing popularity on mobile devices to foster casual creativity. However, the implementation and provision of high-quality image filters for artistic rendering is still faced by the inherent limitations of mobile graphics hardware such as computing power and memory resources. This work presents a mobile implementation of...
Conference Paper
Full-text available
We present Pic2Comic – an application that enables the user to semi-automatically transform photos into cartoons and caricatures interactively. A caricature (lat. "caricare": load, exaggerate) is a picture, description, or imitation of a person or thing in which certain striking characteristics are exaggerated in order to create a comic or grotesqu...
Article
Full-text available
This article presents multi-perspective 3D panoramas that focus on visualizing 3D geovirtual environments (3D GeoVEs) for navigation and exploration tasks. Their key element, a multi-perspective view, seamlessly combines what is seen from multiple viewpoints into a single image. This approach facilitates thepresentation of information for virtual 3...
Article
This paper discusses challenges and approaches of interaction and navigation techniques for multi-perspective views (MPVs) in the context of 3D geovirtual environments. In contrast to single-perspective views, MPVs seamlessly combine multiple views from different perspectives in one image to reduce occlusion and visual clutter while providing addit...
Conference Paper
This paper discusses challenges and approaches of interaction and navigation techniques for multi-perspective views (MPVs) in the context of 3D geovirtual environments. In contrast to single-perspective views, MPVs seamlessly combine multiple views from different perspectives in one image to reduce occlusion and visual clutter while providing addit...
Conference Paper
Full-text available
This paper presents a multi-perspective rendering technique that enables detail+overview visualization and interactive exploration of virtual 3D building model. Virtual 3D building models, as main elements of virtual 3D city models, are used in a growing number of application domains, such as geoanalysis, disaster management and architectural plann...
Presentation
Full-text available
Presentation of Research Paper "Multi-Perspective Detail+Overview Visualization of 3D Building Exploration"
Article
3D geovirtual environments (3D GeoVEs), such as 3D virtual city and landscape models, have become established tools to communicate geoinformation to experts and non-experts of different application domains. In contrast to 2D geovisualization tools (e.g., topographic and thematic maps) 3D GeoVEs primarily depict geoinformation utilizing a perspectiv...
Conference Paper
Full-text available
Virtual 3D city models are essential visualization tools for effective communication of complex urban spatial information. Immersive visualization of virtual 3D city models offers an intuitive access to and an effective way of realization of urban spatial information, enabling new collaborative applications and decision-support systems. This paper...
Conference Paper
Full-text available
Digital mapping services have become fundamental tools in economy and society to provide domain experts and non-experts with customized, multi-layered map contents. In particular because of the continuous advancements in the acquisition, provision, and visualization of virtual 3D city and landscape models, 3D mapping services, today, represent key...
Chapter
Full-text available
3D geovirtual environments (GeoVE), such as virtual 3D city and landscape models become an important tool for the visualization of geospatial information. Highlighting is an important component within a visualization framework and is essential for the user interaction within many applications. It enables the user to easily perceive active or select...
Article
Full-text available
3D geovirtual environments (GeoVEs), such as virtual 3D city models or landscape models, are essential visualization tools for effectively communicating complex spatial information. In this paper, we discuss how these environments can be visualized using multi-perspective projections based on view-dependent global deformations. Multi-perspective pr...
Conference Paper
Full-text available
3D geovirtual environments (GeoVE), such as virtual 3D city and landscape models became an important tool for the visualization of geospatial information. Highlighting is an important component within a visualization framework and is essential for the user interaction within many applications. It enables the user to easily perceive active or select...
Presentation
Full-text available
Presentation of Research Paper "Interactive Rendering Techniques for Highlighting in 3D Geovirtual Environments"

Network

Cited By

Projects

Projects (4)
Archived project
Objective of this project are real-time rendering techniques and applications for focus+context visualization of interactive 3D geovirtual environments such as virtual 3D city and landscape models. These environments are generally characterized by a large number of objects and are of high complexity with respect to geometry and textures. For these reasons, their interactive 3D rendering represents a major challenge. Their 3D depiction implies a number of weaknesses such as occlusions, cluttered image contents, and partial screen-space usage. To overcome these limitations and, thus, to facilitate the effective communication of geo-information, principles of focus+context visualization can be used for the design of real-time 3D rendering techniques for 3D geovirtual environments. In general, detailed views of a 3D geovirtual environment are combined seamlessly with abstracted views of the context within a single image. To perform the real-time image synthesis required for interactive visualization, dedicated parallel processors (GPUs) for rasterization of computer graphics primitives are used. For this purpose, the design and implementation of appropriate data structures and rendering pipelines are required.
Archived project
The computation and selection of the abstraction level of 3D geospatial model contents according to user interaction and dynamically changing thematic information by using principles of artistic rendering, cartographic generalization, and 3D semiotics.