Sebastian Hartwig

Sebastian Hartwig

Auto-generated profile, based on publicly available information

Sebastian Hartwig

Visual Computing Group, Ulm University, Ulm, Germany

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
1 July 2025 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
SHSebastian Hartwig
Sebastian Hartwig
DEDominik Engel
Dominik Engel
LSLeon Sick
Leon Sick
HKHannah Kniesel
Hannah Kniesel
TPTristan Payer
Tristan Payer
TRTimo Ropinski
Timo Ropinski
AI-based text-to-image models do not only excel at generating realistic images, they also give designers more and more fine-grained control over the image content. Consequently, these approaches have gathered increased attention within the computer graphics research community, which has been historically devoted towards traditional rendering techniques, that offer precise control over scene parameters (e.g., objects, materials, and lighting). While the quality of conventionally rendered images is assessed through well established image quality metrics, such as SSIM or PSNR, the unique challenges of text-to-image generation require other, dedicated quality metrics. These metrics must be able to not only measure overall image quality, but also how well images reflect given text prompts, whereby the control of scene and rendering parameters is interweaved. Within this survey, we provide a comprehensive overview of such text-to-image quality metrics, and propose a taxonomy to categorize these metrics. Our taxonomy is grounded in the assumption, that there are two main quality criteria, namely compositional quality and general quality, that contribute to the overall image quality. Besides the metrics, this survey covers dedicated text-to-image benchmark datasets, over which the metrics are frequently computed. Finally, we identify limitations and open challenges in the field of text-to-image generation, and derive guidelines for practitioners conducting text-to-image evaluation.

19 July 2022 in Computer Graphics Forum
Verified
Journal Article
Open access
SHS. Hartwig
S. Hartwig
MSM. Schelling
M. Schelling
COC. V. Onzenoodt
C. V. Onzenoodt
PVPere-Pau Vázquez
Pere-Pau Vázquez
PHP. Hermosilla
P. Hermosilla
TRT. Ropinski
T. Ropinski
View quality measures compute scores for given views and are used to determine an optimal view in viewpoint selection tasks. Unfortunately, despite the wide adoption of these measures, they are rather based on computational quantities, such as entropy, than human preferences. To instead tailor viewpoint measures towards humans, view quality measures need to be able to capture human viewpoint preferences. Therefore, we introduce a large‐scale crowdsourced data set, which contains 58k annotated viewpoints for 3220 ModelNet40 models. Based on this data, we derive a neural view quality measure abiding to human preferences. We further demonstrate that this view quality measure not only generalizes to models unseen during training, but also to unseen model categories. We are thus able to predict view qualities for single images, and directly predict human preferred viewpoints for 3D models by exploiting point‐based learning technology, without requiring to generate intermediate images or sampling the view sphere. We will detail our data collection procedure, describe the data analysis and model training and will evaluate the predictive quality of our trained viewpoint measure on unseen models and categories. To our knowledge, this is the first deep learning approach to predict a view quality measure solely based on human preferences.

17 May 2013 in Ecography
Verified
Journal Article
Closed access
PDF file
TMThomas Mehner
Thomas Mehner
MEMatthias Emmrich
Matthias Emmrich
SHSebastian Hartwig
Sebastian Hartwig

22 August 2024 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Verified
Journal Article
Open access
MCMark Colley
Mark Colley
SHSebastian Hartwig
Sebastian Hartwig
AZAlbin Zeqiri
Albin Zeqiri
TRTimo Ropinski
Timo Ropinski
EREnrico Rukzio
Enrico Rukzio
Thermal comfort inside buildings is a well-studied field where human judgment for thermal comfort is collected and may be used for automatic thermal comfort estimation. However, indoor scenarios are rather static in terms of thermal state changes and, thus, cannot be applied to dynamic conditions, e.g., inside a vehicle. In this work, we present our findings of a gap between building and in-vehicle scenarios regarding thermal comfort estimation. We provide evidence by comparing deep neural classifiers for thermal comfort estimation for indoor and in-vehicle conditions. Further, we introduce a temporal dataset for indoor predictions incorporating 31 input signals and self-labeled user ratings by 18 subjects in a self-built climatic chamber. For in-vehicle scenarios, we acquired a second dataset featuring human judgments from 20 subjects in a BMW 3 Series. Our experimental results indicate superior performance for estimations from time series data over single vector input. Leveraging modern machine learning architectures enables us to recognize human thermal comfort states and estimate future states automatically. We provide details on training a recurrent network-based classifier and perform an initial performance benchmark of the proposed dataset. Ultimately, we compare our collected dataset to publicly available thermal comfort datasets.

15 February 2023 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Open access
DEDominik Engel
Dominik Engel
SHSebastian Hartwig
Sebastian Hartwig
TRTimo Ropinski
Timo Ropinski
Neural networks have shown great success in extracting geometric information from color images. Especially, monocular depth estimation networks are increasingly reliable in real-world scenes. In this work we investigate the applicability of such monocular depth estimation networks to semi-transparent volume rendered images. As depth is notoriously difficult to define in a volumetric scene without clearly defined surfaces, we consider different depth computations that have emerged in practice, and compare state-of-the-art monocular depth estimation approaches for these different interpretations during an evaluation considering different degrees of opacity in the renderings. Additionally, we investigate how these networks can be extended to further obtain color and opacity information, in order to create a layered representation of the scene based on a single color image. This layered representation consists of spatially separated semi-transparent intervals that composite to the original input rendering. In our experiments we show that existing approaches to monocular depth estimation can be adapted to perform well on semi-transparent volume renderings, which has several applications in the area of scientific visualization, like re-composition with additional objects and labels or additional shading.

27 December 2024 in Computer Graphics Forum
Verified
Journal Article
Open access
SHS. Hartwig
S. Hartwig
COC. V. Onzenoodt
C. V. Onzenoodt
DED. Engel
D. Engel
PHP. Hermosilla
P. Hermosilla
TRT. Ropinski
T. Ropinski
Cluster separation is a task typically tackled by widely used clustering techniques, such as k‐means or DBSCAN. However, these algorithms are based on non‐perceptual metrics, and our experiments demonstrate that their output does not reflect human cluster perception. To bridge the gap between human cluster perception and machine‐computed clusters, we propose HPSCAN, a learning strategy that operates directly on scattered data. To learn perceptual cluster separation on such data, we crowdsourced the labeling of bivariate (scatterplot) datasets to 384 human participants. We train our HPSCAN model on these human‐annotated data. Instead of rendering these data as scatterplot images, we used their x and y point coordinates as input to a modified PointNet++ architecture, enabling direct inference on point clouds. In this work, we provide details on how we collected our dataset, report statistics of the resulting annotations, and investigate the perceptual agreement of cluster separation for real‐world data. We also report the training and evaluation protocol for HPSCAN and introduce a novel metric, that measures the accuracy between a clustering technique and a group of human annotators. We explore predicting point‐wise human agreement to detect ambiguities. Finally, we compare our approach to 10 established clustering techniques and demonstrate that HPSCAN is capable of generalizing to unseen and out‐of‐scope data.