no code implementations • 18 Dec 2024 • Sebastian Koch, Johanna Wald, Mirco Colosi, Narunas Vaskevicius, Pedro Hermosilla, Federico Tombari, Timo Ropinski
Neural radiance fields are an emerging 3D scene representation and recently even been extended to learn features for scene understanding by distilling open-vocabulary features from vision-language models.
no code implementations • 25 Nov 2024 • Leon Sick, Dominik Engel, Sebastian Hartwig, Pedro Hermosilla, Timo Ropinski
Traditionally, algorithms that learn to segment object instances in 2D images have heavily relied on large amounts of human-annotated data.
Ranked #1 on
Unsupervised Instance Segmentation
on COCO val2017
1 code implementation • 18 Oct 2024 • Daniel Wolf, Tristan Payer, Catharina Silvia Lisson, Christoph Gerhard Lisson, Meinrad Beer, Michael Götz, Timo Ropinski
The effect of these different reduction strategies on contrastive learning is evaluated on two pre-training datasets and several downstream classification tasks.
no code implementations • 18 Mar 2024 • Sebastian Hartwig, Dominik Engel, Leon Sick, Hannah Kniesel, Tristan Payer, Poonam Poonam, Michael Glöckler, Alex Bäuerle, Timo Ropinski
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.
no code implementations • 23 Feb 2024 • Leon Sick, Dominik Engel, Pedro Hermosilla, Timo Ropinski
Masked autoencoders (MAEs) have established themselves as a powerful method for unsupervised pre-training for computer vision tasks.
1 code implementation • CVPR 2024 • Sebastian Koch, Narunas Vaskevicius, Mirco Colosi, Pedro Hermosilla, Timo Ropinski
We co-embed the features from a 3D scene graph prediction backbone with the feature space of powerful open world 2D vision language foundation models.
no code implementations • 25 Oct 2023 • Sebastian Koch, Pedro Hermosilla, Narunas Vaskevicius, Mirco Colosi, Timo Ropinski
While it is widely accepted that pre-training is an effective approach to improve model performance in low data regimes, in this paper, we find that existing pre-training methods are ill-suited for 3D scene graphs.
no code implementations • 27 Sep 2023 • Sebastian Koch, Pedro Hermosilla, Narunas Vaskevicius, Mirco Colosi, Timo Ropinski
In the field of 3D scene understanding, 3D scene graphs have emerged as a new scene representation that combines geometric and semantic information about objects and their relationships.
no code implementations • CVPR 2024 • Leon Sick, Dominik Engel, Pedro Hermosilla, Timo Ropinski
We achieve this by (1) learning depth-feature correlation by spatially correlate the feature maps with the depth maps to induce knowledge about the structure of the scene and (2) implementing farthest-point sampling to more effectively select relevant features by utilizing 3D sampling techniques on depth information of the scene.
no code implementations • 4 Sep 2023 • Dominik Engel, Leon Sick, Timo Ropinski
In volume rendering, transfer functions are used to classify structures of interest, and to assign optical properties such as color and opacity.
1 code implementation • 12 Aug 2023 • Daniel Wolf, Tristan Payer, Catharina Silvia Lisson, Christoph Gerhard Lisson, Meinrad Beer, Michael Götz, Timo Ropinski
Based on our results, we propose the SparK pre-training for medical imaging tasks with only small annotated datasets.
1 code implementation • 27 Apr 2023 • Sebastian Hartwig, Christian van Onzenoodt, Dominik Engel, Pedro Hermosilla, Timo Ropinski
Cluster separation is a task typically tackled by widely used clustering techniques, such as k-means or DBSCAN.
1 code implementation • 2 Apr 2023 • Patrik Puchert, Poonam Poonam, Christian van Onzenoodt, Timo Ropinski
To support such stratified evaluations, we propose LLMMaps as a novel visualization technique that enables users to evaluate LLMs' performance with respect to Q&A datasets.
1 code implementation • 11 Oct 2022 • Michael Schelling, Pedro Hermosilla, Timo Ropinski
Indirect Time-of-Flight (iToF) cameras are a widespread type of 3D sensor, which perform multiple captures to obtain depth values of the captured scene.
1 code implementation • 27 Jun 2022 • Dominik Engel, Sebastian Hartwig, Timo Ropinski
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.
no code implementations • 20 Jun 2022 • Alex Bäuerle, Daniel Jönsson, Timo Ropinski
Promising methods for discovering learned features are based on analyzing activation values, whereby current techniques focus on analyzing high activation values to reveal interesting features on a neuron level.
no code implementations • 31 May 2022 • Pedro Hermosilla, Timo Ropinski
Learning from 3D protein structures has gained wide interest in protein modeling and structural bioinformatics.
no code implementations • 8 May 2022 • Ngan Nguyen, Feng Liang, Dominik Engel, Ciril Bohak, Peter Wonka, Timo Ropinski, Ivan Viola
We propose a new microscopy simulation system that can depict atomistic models in a micrograph visual style, similar to results of physical electron microscopy imaging.
1 code implementation • CVPR 2022 • Hannah Kniesel, Timo Ropinski, Tim Bergner, Kavitha Shaga Devan, Clarissa Read, Paul Walther, Tobias Ritschel, Pedro Hermosilla
Scanning Transmission Electron Microscopes (STEMs) acquire 2D images of a 3D sample on the scale of individual cell components.
1 code implementation • ICLR 2022 • Adam Celarek, Pedro Hermosilla, Bernhard Kerbl, Timo Ropinski, Michael Wimmer
This paper proposes a novel method for deep learning based on the analytical convolution of multidimensional Gaussian mixtures.
1 code implementation • 17 Jan 2022 • Alex Bäuerle, Aybuke Gul Turker, Ken Burke, Osman Aka, Timo Ropinski, Christina Greer, Mani Varadarajan
With our approach, different models and datasets for large label spaces can be systematically and visually analyzed and compared to make informed fairness assessments tackling problematic bias.
no code implementations • 7 Dec 2021 • Pedro Hermosilla, Michael Schelling, Tobias Ritschel, Timo Ropinski
Appropriate weight initialization has been of key importance to successfully train neural networks.
1 code implementation • CVPR 2022 • Michael Schelling, Pedro Hermosilla, Timo Ropinski
Time-of-Flight (ToF) cameras are subject to high levels of noise and distortions due to Multi-Path-Interference (MPI).
no code implementations • 23 Jul 2021 • Patrik Puchert, Timo Ropinski
Conventional methods for human pose estimation either require a high degree of instrumentation, by relying on many inertial measurement units (IMUs), or constraint the recording space, by relying on extrinsic cameras.
1 code implementation • 23 Jul 2021 • Patrik Puchert, Pedro Hermosilla, Tobias Ritschel, Timo Ropinski
Density estimation plays a crucial role in many data analysis tasks, as it infers a continuous probability density function (PDF) from discrete samples.
no code implementations • 4 Apr 2021 • Ngan Nguyen, Ciril Bohak, Dominik Engel, Peter Mindek, Ondřej Strnad, Peter Wonka, Sai Li, Timo Ropinski, Ivan Viola
Our technique shows the high impact in target sciences for visual data analysis of very noisy volumes that cannot be visualized with existing techniques.
no code implementations • 9 Dec 2020 • Alex Bäuerle, Patrick Albus, Raphael Störk, Tina Seufert, Timo Ropinski
In an empirical study, we assessed 37 subjects in a between-subjects design to investigate the learning outcomes and cognitive load of exploRNN compared to a classic text-based learning environment.
1 code implementation • 19 Aug 2020 • Dominik Engel, Timo Ropinski
We present a novel deep learning based technique for volumetric ambient occlusion in the context of direct volume rendering.
1 code implementation • ICLR 2021 • Pedro Hermosilla, Marco Schäfer, Matěj Lang, Gloria Fackelmann, Pere Pau Vázquez, Barbora Kozlíková, Michael Krone, Tobias Ritschel, Timo Ropinski
Proteins perform a large variety of functions in living organisms, thus playing a key role in biology.
1 code implementation • 10 Mar 2020 • Michael Schelling, Pedro Hermosilla, Pere-Pau Vazquez, Timo Ropinski
Optimal viewpoint prediction is an essential task in many computer graphics applications.
1 code implementation • 13 Feb 2020 • Gabriel Eilertsen, Daniel Jönsson, Timo Ropinski, Jonas Unger, Anders Ynnerman
of neural network classifiers, and train a large number of models to represent the weight space.
1 code implementation • ICCV 2019 • Pedro Hermosilla, Tobias Ritschel, Timo Ropinski
We show that denoising of 3D point clouds can be learned unsupervised, directly from noisy 3D point cloud data only.
no code implementations • 29 Mar 2019 • Sebastian Hartwig, Timo Ropinski
While synthesized data sets can be used to overcome this challenge, it is important that these data sets close the reality gap, i. e., a model trained on synthetic image data is able to generalize to real images.
1 code implementation • 11 Feb 2019 • Alex Bäuerle, Christian van Onzenoodt, Timo Ropinski
To convey neural network architectures in publications, appropriate visualizations are of great importance.
1 code implementation • 12 Nov 2018 • Pedro Hermosilla, Sebastian Maisch, Tobias Ritschel, Timo Ropinski
Thus, we suggest a two-stage operator comprising of a 3D network that first transforms the point cloud into a latent representation, which is later on projected to the 2D output image using a dedicated 3D-2D network in a second step.
1 code implementation • 9 Aug 2018 • Alex Bäuerle, Heiko Neumann, Timo Ropinski
We thus propose a novel approach that uses the power of pretrained classifiers to visually guide users to noisy labels, and let them interactively check error candidates, to iteratively improve the training data set.
1 code implementation • 5 Jun 2018 • Pedro Hermosilla, Tobias Ritschel, Pere-Pau Vázquez, Àlvar Vinacua, Timo Ropinski
We propose an efficient and effective method to learn convolutions for non-uniformly sampled point clouds, as they are obtained with modern acquisition techniques.