Research and Development

Years of passionate research in computer graphics, computer vision and machine learning results in cutting edge technology that enables our users to transform images in unique pieces of art. We at Digital Masterpieces beliefe that sharing research results with the community fosters innovation. Our goal is to research and develop technology that effectively helps our users to ease their creative process.

Sneak Peeks

Custom Style Transfer 

4th September 2024

Here’s a sneak peak into our new feature, Custom Style Transfer. Upload any image and apply its style to your photos seamlessly. Watch the demo to see it in action!

You are currently viewing a placeholder content from YouTube. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.

More Information

Custom Styles 

1st December 2023

With Custom Styles you can personalize and save your very own styles with ease. Use our curated styles as a starting point, fine-tune them to your likings and save them as your new, personalized, very own Custom Style. Custom Styles are synchronized among all your devices, so that you can apply them on any device, everywhere, any time.

You are currently viewing a placeholder content from YouTube. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.

More Information

Publications

Featured / Highlights

Interactive Control over Temporal Consistency while Stylizing Video Streams  

Computer Graphics Forum (Proc. Eurographics Symposium on Rendering) 2023
Sumit Shekhar, Max Reimann, Moritz Hilscher, Amir Semmo, Jürgen Döllner, and Matthias Trapp
DOI Project Page PaperCode (GitHub)

WISE: Whitebox Image Stylization by Example-based Learning

European Conference on Computer Vision (ECCV) 2022
Winfried Lötzsch, Max Reimann, Martin Büßemeyer, Amir Semmo, Jürgen Döllner, and Matthias Trapp
DOI, Paper (PDF), Project Page, Code (GitHub), Online Demo (Hugging Face)

Controlling Strokes in Fast Neural Style Transfer using Content Transforms

The Visual Computer 2022
Max Reimann, Benito Buchheim, Amir Semmo, Jürgen Döllner, and Matthias Trapp
DOI, Paper (PDF)

Trios: Stylistic Rendering of 3D Photos

ACM SIGGRAPH Appy Hour 2022
Ulrike Bath, Sumit Shekhar, Hendrik Tjabben, Amir Semmo, Sebastian Pasewaldt, Jürgen Döllner, and Matthias Trapp
DOI

CERVI: Collaborative Editing of Raster and Vector Images

The Visual Computer 2022
Ulrike Bath, Julian Egbert, Julian Schmidt, Amir Semmo, Jürgen Döllner, and Matthias Trapp
DOI, Paper (PDF)

Interactive Photo Editing on Smartphones via Intrinsic Decomposition

Computer Graphics Forum (Proceedings Eurographics) 2021
Sumit Shekhar, Max Reimann, Maximilian Mayer, Amir Semmo, Sebastian Pasewaldt, Jürgen Döllner, and Matthias Trapp
DOI, Project Page, Paper – HQ (PDF), Paper – Optimized (PDF), Supplemental Material (PDF)

Forward Selfies 

ACM SIGGRAPH Appy Hour 2021
Philipp Trenz, Sebastian Pasewaldt, Mandy Klingbeil, Jürgen Döllner, and Matthias Trapp
DOI

MotionViz: Artistic Visualization of Human Motion on Mobile Devices

ACM SIGGRAPH Appy Hour 2021
Maximilian Mayer, Philipp Trenz, Sebastian Pasewaldt, Mandy Klingbeil, Jürgen Döllner, Matthias Trapp, and Amir Semmo
DOI, Video (YouTube)

StyleTune: Interactive Style Transfer Enhancement on Mobile Devices

ACM SIGGRAPH Appy Hour 2021
Benito Buchheim, Max Reimann, Sebastian Pasewaldt, Jürgen Döllner, and Matthias Trapp
DOI

Graphite: Interactive Photo-to-Drawing Stylization on Mobile Devices

ACM SIGGRAPH Appy Hour 2020
Amir Semmo and Sebastian Pasewaldt
DOI

Locally Controllable Neural Style Transfer on Mobile Devices

The Visual Computer 2019
Max Reimann, Mandy Klingbeil, Sebastian Pasewaldt, Amir Semmo, Matthias Trapp, and Jürgen Döllner
DOI, Paper (PDF)

ViVid: Depicting Dynamics in Stylized Live Photos

ACM SIGGRAPH Appy Hour 2019
Amir Semmo, Max Reimann, Mandy Klingbeil, Sumit Shekhar, Matthias Trapp, and Jürgen Döllner
DOI, Paper (PDF)

MaeSTrO: Mobile-Style Transfer Orchestration Using Adaptive Neural Networks

ACM SIGGRAPH Appy Hour 2018
Max Reimann, Amir Semmo, Sebastian Pasewaldt, Mandy Klingbeil, and Jürgen Döllner
DOI, Paper (PDF)

Pictory: Combining Neural Style Transfer and Image Filtering

ACM SIGGRAPH Appy Hour 2017
Amir Semmo, Matthias Trapp, Jürgen Döllner, and Mandy Klingbeil
DOI, Paper (PDF)

Interactive Image Filtering with Multiple Levels-of-Control on Mobile Devices

SIGGRAPH Asia Symposium on Mobile Graphics and Interactive Applications 2016
Amir Semmo, Tobias Dürschmid, Matthias Trapp, Mandy Klingbeil, Jürgen Döllner, and Sebastian Pasewaldt
DOI, Paper (PDF), Filter Results (Images / ZIP, 34 MiB)

BeCasso: Image Stylization by Interactive Oil Paint Filtering on Mobile Devices

ACM SIGGRAPH Appy Hour 2016
Amir Semmo, Jürgen Döllner, and Frank Schlegel
DOI, Paper (PDF)

A Framework for Art-directed Augmentation of Human Motion in Videos on Mobile Devices

International Conference on Computer Graphics, Visualization and Computer Vision (WSCG) 2023
Rosmarie Debski, Ole Schmitt, Philipp Trenz, Max Reimann, Jürgen Döllner, Matthias Trapp, Amir Semmo, and Sebastian Pasewaldt
DOI, Paper (PDF)


ALIVE: Adaptive-Chromaticity for Interactive Low-light Image and Video Enhancement

International Conference on Computer Graphics, Visualization and Computer Vision (WSCG) 2023
Sumit Shekhar, Max Reimann, Jobin Idiculla Wattaseril, Amir Semmo, Jürgen Döllner, and Matthias Trapp
DOI, Paper (PDF)


A Service-Based Preset Recommendation System for Image Stylization Applications

Proc. VISIGRAPP 2023
Florian Fregien, Fabian Galandi, Max Reimann, Sebastian Pasewaldt, Jürgen Döllner, and Matthias Trapp
DOI


Design Space of Geometry-based Image Abstraction Techniques with Vectorization Applications

International Conference on Computer Graphics, Visualization and Computer Vision (WSCG) 2022
Lisa Ihde, Amir Semmo, Jürgen Döllner, and Matthias Trapp
Paper (PDF)


Interactive Multi-level Stroke Control for Neural Style Transfer

International Conference on Cyberworlds 2021
Max Reimann, Benito Buchheim, Amir Semmo, Jürgen Döllner, and Matthias Trapp
DOI, Paper (PDF)


COLiER: Collaborative Editing of Raster Images

International Conference on Cyberworlds 2021
Ulrike Bath, Sumit Shekhar, Jürgen Döllner, and Matthias Trapp
DOI


Service-based Analysis and Abstraction for Content Moderation of Digital Images

International Conference on Graphics Interface 2021
Moritz Hilscher, Hendrik Tjabben, Hendrik Rätz, Amir Semmo, Lonni Besançon, Jürgen Döllner, and Matthias Trapp
DOI, Paper (PDF), URL (OpenReview)


Integration of Image Processing Techniques into the Unity Game Engine 

International Conference on Image Processing and Vision Engineering 2021
Leon Masopust, Sebastian Pasewaldt, Jürgen Döllner, and Matthias Trapp
DOI


Service-based Processing of Gigapixel Images 

Proc. WSCG 2021
Florian Fregien, Sebastian Pasewaldt, Jürgen Döllner, and Matthias Trapp
DOI


Teaching Data-driven Video Processing via Crowdsourced Data Collection

Eurographics Education Papers 2021
Max Reimann, Ole Wegen, Sebastian Pasewaldt, Amir Semmo, Matthias Trapp, and Jürgen Döllner
DOI


Consistent Filtering Of Videos And Dense Light-Fields Without Optic-Flow

International Symposium on Vision, Modeling, and Visualization (VMV) 2019
Sumit Shekhar, Amir Semmo, Matthias Trapp, Okan Tarhan Tursun, Sebastian Pasewaldt, Karol Myszkowski, and Jürgen Döllner
DOI, Project Page, Paper (PDF)


Techniques for GPU-based Color Palette Mapping

WSCG 2019
Matthias Trapp, Sebastian Pasewaldt, and Jürgen Döllner
DOI, Paper (PDF)


Performance Evaluation and Comparison of Service-based Image Processing based on Software Rendering

WSCG 2019
Ole Wegen, Matthias Trapp, Jürgen Döllner, and Sebastian Pasewaldt
DOI, Paper (PDF)


MaeSTrO: A Mobile App for Style Transfer Orchestration using Neural Networks

International Conference on Cyberworlds 2018
Max Reimann, Mandy Klingbeil, Sebastian Pasewaldt, Amir Semmo, Jürgen Döllner, and Matthias Trapp
Paper (PDF), Presentation Slides (PDF), DOI


Approaches for Local Artistic Control of Mobile Neural Style Transfer

Expressive Poster Session 2018
Max Reimann, Mandy Klingbeil, Sebastian Pasewaldt, Amir Semmo, Jürgen Döllner, and Matthias Trapp
DOI, Paper (PDF)


Teaching Image-Processing Programming for Mobile Devices: A Software Development Perspective

Eurographics Education Papers 2018
Matthias Trapp, Sebastian Pasewaldt, Tobias Dürschmid, Amir Semmo, and Jürgen Döllner
DOI, Paper (PDF)


Challenges in User Experience Design of Image Filtering Apps

SIGGRAPH Asia Symposium on Mobile Graphics and Interactive Applications 2017
Mandy Klingbeil, Sebastian Pasewaldt, Amir Semmo, and Jürgen Döllner
DOI, Paper (PDF)


Demo: Pictory – Neural Style Transfer and Editing with CoreML

SIGGRAPH Asia Symposium on Mobile Graphics and Interactive Applications (Demo) 2017
Sebastian Pasewaldt, Amir Semmo, Mandy Klingbeil, and Jürgen Döllner
DOI, Paper (PDF)


BeCasso: Artistic Image Processing and Editing on Mobile Devices

SIGGRAPH Asia Symposium on Mobile Graphics and Interactive Applications (Demo) 2016
Sebastian Pasewaldt, Amir Semmo, Jürgen Döllner, and Frank Schlegel
DOI, Paper (PDF)


Interactive Multi-scale Oil Paint Filtering on Mobile Devices

ACM SIGGRAPH Posters 2016
Amir Semmo, Mattias Trapp, Tobias Dürschmid, Jürgen Döllner, and Sebastian Pasewaldt
DOI, Paper (PDF)


Interactive Oil Paint Filtering On Mobile Devices

Expressive Poster Session 2016
Amir Semmo, Matthias Trapp, Sebastian Pasewaldt, and Jürgen Döllner
DOI, Paper (PDF)

Funding Projects

The aim of the project is to drastically simplify the application of advanced NST-based transformation and stylizations algorithms for users by utilizing machine learning to predict optimal design and configuration parameters for a given input image. The process to be developed will significantly expand and simplify IT for the automatic transformation and interactive design of digital images using artificial intelligence methods for end users, as well as enable the use of the underlying highly innovative IT building blocks in third-party IT solutions. The predicted optimal parameter configurations enable a much more efficient application of NST-based transformation and design procedures,, the optimization of existing and future state-of-the-art processes, as well as the provision of fully and partially automated image transformation solutions.

Funding Agency: Federal Ministry for Economic Affairs and Climate Action
Funding Number: 16KN086470
Research Partner: XU Exponential University of Applied Sciences GmbH

This project aims on researching and developing a software framework that is capable to enhance and process multidimensional video streams. In contrast to traditional video streams, multidimensional video streams contain additional information, such as depth, optical flow and semantic information. The mdViPro framework will form the basis for new and innovative Visual Computing and Smart-Graphics applications for end-users as well as companies that are creating, managing, processing and disseminating visual media. 

Funding Agency: Federal Ministry of Education and Research
Funding Number: 01IS18092A
Research Partners: Hasso Plattner Institute, University of Potsdam & GraphicsMedia Network

This project aims to develop a software framework for automatic video abstraction by combining video analysis techniques together with state-of-the-art video abstraction techniques. The AVA framework forms the basis for end-user focussed mobile apps for visual story telling as well as for API and software-as-a-service solutions for companies that generating and processing images and videos, e.g., printing services and social media platforms.

Funding Agency: Federal Ministry of Education and Research
Funding Number: 01IS15041A
Research Partners: Hasso Plattner Institute, University of Potsdam

This project focuses on a tight cooperation of young talents from academia and Digital Masterpieces to foster the exchange of know-how from academia and business.  As part of this project, we implemented concepts and techniques for efficient and effective rendering of stylized images and video, and evaluated approaches for continuous integration and deployment.

The project is funded by the European Social Fund (ESF) and the Federal State of Brandenburg via the Brandenburg Ministry for Labour, Social Affairs, Health, Women and Family (MASGF).

Funding Agency: Investitionsbank des Landes Brandenburg; ESF, MASGF
Funding Number: 85034568

As part of our joint research projects, Digital Masterpieces is tightly cooperating with young talents from academia. Extraordinary bachelor and master thesis that have a strong impact on research and development or the success of the research projects are awarded with the Digital Masterpieces Excellence Award. The award is endowed with a cash amount or a hardware prize.

Awardees:

Maik Zarnbach – 2020 for his Master Thesis “Design and Implementation of an Application Framework for Interactive Image Stylization”
 
In his master thesis, Maik Zarnbach demonstrated his extraordinary technical and research skills by designing and implementing a concept for a macOS-based framework for image transformation applications. Beside tackling several deep-tech challenges related to implementing a high-performance image processing prototype, the full-stack development of the prototype as well as the user-centric design demonstrate his excellent skillset.