Max Reimann

Max Reimann

Auto-generated profile, based on publicly available information

Max Reimann

Hasso Plattner Institute for Digital Engineering University of Potsdam Germany

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 June 2022 in The Visual Computer
Verified
Journal Article
Open access
PDF file
MRMax Reimann
Max Reimann
BBBenito Buchheim
Benito Buchheim
ASAmir Semmo
Amir Semmo
JDJürgen Döllner
Jürgen Döllner
MTMatthias Trapp
Matthias Trapp
Fast style transfer methods have recently gained popularity in art-related applications as they make a generalized real-time stylization of images practicable. However, they are mostly limited to one-shot stylizations concerning the interactive adjustment of style elements. In particular, the expressive control over stroke sizes or stroke orientations remains an open challenge. To this end, we propose a novel stroke-adjustable fast style transfer network that enables simultaneous control over the stroke size and intensity, and allows a wider range of expressive editing than current approaches by utilizing the scale-variance of convolutional neural networks. Furthermore, we introduce a network-agnostic approach for style-element editing by applying reversible input transformations that can adjust strokes in the stylized output. At this, stroke orientations can be adjusted, and warping-based effects can be applied to stylistic elements, such as swirls or waves. To demonstrate the real-world applicability of our approach, we present StyleTune, a mobile app for interactive editing of neural style transfers at multiple levels of control. Our app allows stroke adjustments on a global and local level. It furthermore implements an on-device patch-based upsampling step that enables users to achieve results with high output fidelity and resolutions of more than 20 megapixels. Our approach allows users to art-direct their creations and achieve results that are not possible with current style transfer applications.

26 July 2023 in Computer Graphics Forum
Verified
Journal Article
Open access
SSSumit Shekhar
Sumit Shekhar
MRMax Reimann
Max Reimann
MHMoritz Hilscher
Moritz Hilscher
ASAmir Semmo
Amir Semmo
JDJürgen Döllner
Jürgen Döllner
MTMatthias Trapp
Matthias Trapp
Image stylization has seen significant advancement and widespread interest over the years, leading to the development of a multitude of techniques. Extending these stylization techniques, such as Neural Style Transfer (NST), to videos is often achieved by applying them on a per‐frame basis. However, per‐frame stylization usually lacks temporal consistency, expressed by undesirable flickering artifacts. Most of the existing approaches for enforcing temporal consistency suffer from one or more of the following drawbacks: They (1) are only suitable for a limited range of techniques, (2) do not support online processing as they require the complete video as input, (3) cannot provide consistency for the task of stylization, or (4) do not provide interactive consistency control. Domain‐agnostic techniques for temporal consistency aim to eradicate flickering completely but typically disregard aesthetic aspects. For stylization tasks, however, consistency control is an essential requirement as a certain amount of flickering adds to the artistic look and feel. Moreover, making this control interactive is paramount from a usability perspective. To achieve the above requirements, we propose an approach that stylizes video streams in real‐time at full HD resolutions while providing interactive consistency control. We develop a lite optical‐flow network that operates at 80 Frames per second (FPS) on desktop systems with sufficient accuracy. Further, we employ an adaptive combination of local and global consistency features and enable interactive selection between them. Objective and subjective evaluations demonstrate that our method is superior to state‐of‐the‐art video consistency approaches. maxreimann.github.io/stream‐consistency

1 May 2021 in Computer Graphics Forum
Verified
Journal Article
Open access
PDF file
SSSumit Shekhar
Sumit Shekhar
MRMax Reimann
Max Reimann
MMMaximilian Mayer
Maximilian Mayer
ASAmir Semmo
Amir Semmo
SPSebastian Pasewaldt
Sebastian Pasewaldt
MTMatthias Trapp
Matthias Trapp
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, intrinsic scene decomposition can be facilitated using depth‐based priors, which nowadays is easy to acquire with high‐end smartphones by utilizing their depth sensors. In this work, we present a system for intrinsic decomposition of RGB‐D images on smartphones and the algorithmic as well as design choices therein. Unlike state‐of‐the‐art methods that assume only diffuse reflectance, we consider both diffuse and specular pixels. For this purpose, we present a novel specularity extraction algorithm based on a multi‐scale intensity decomposition and chroma inpainting. At this, the diffuse component is further decomposed into albedo and shading components. We use an inertial proximal algorithm for non‐convex optimization (iPiano) to ensure albedo sparsity. Our GPU‐based visual processing is implemented on iOS via the Metal API and enables interactive performance on an iPhone 11 Pro. Further, a qualitative evaluation shows that we are able to obtain high‐quality outputs. Furthermore, our proposed approach for specularity removal outperforms state‐of‐the‐art approaches for real‐world images, while our albedo and shading layer decomposition is faster than the prior work at a comparable output quality. Manifold applications such as recoloring, retexturing, relighting, appearance editing, and stylization are shown, each using the intrinsic layers obtained with our method and/or the corresponding depth data.

17 April 2019 in The Visual Computer
Verified
Journal Article
Closed access
PDF file
MRMax Reimann
Max Reimann
MKMandy Klingbeil
Mandy Klingbeil
SPSebastian Pasewaldt
Sebastian Pasewaldt
ASAmir Semmo
Amir Semmo
MTMatthias Trapp
Matthias Trapp
JDJürgen Döllner
Jürgen Döllner

24 October 2022
Verified
Book Chapter
Closed access
PDF file
WLWinfried Lötzsch
Winfried Lötzsch
MRMax Reimann
Max Reimann
MBMartin Büssemeyer
Martin Büssemeyer
ASAmir Semmo
Amir Semmo
JDJürgen Döllner
Jürgen Döllner
MTMatthias Trapp
Matthias Trapp

5 August 2021
Verified
Conference Paper
Open access
BBBenito Buchheim
Benito Buchheim
MRMax Reimann
Max Reimann
SPSebastian Pasewaldt
Sebastian Pasewaldt
JDJürgen Döllner
Jürgen Döllner
MTMatthias Trapp
Matthias Trapp
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 continuous and seamless edits through a unified stroke-size representation in the feature space of the style transfer network. StyleTune introduces a three-stage user interface, that enables users to first explore global stroke parametrizations for a chosen NST. They can then interactively locally retouch the stroke size and orientation using brush metaphors. Finally, high resolution outputs of 20 Megapixels and more can be obtained using a patch-based upsampling and local detail transfer approach, that transfers small-scale details such as paint-bristles and canvas structure. The app uses Apple’s CoreML and Metal APIs for efficient on-device processing.