no code implementations • 23 Apr 2024 • Alina Pleli, Simon Baeuerle, Michel Janus, Jonas Barth, Ralf Mikut, Hendrik P. A. Lensch
Unsupervised clustering of wafer map defect patterns is challenging because the appearance of certain defect patterns varies significantly.
no code implementations • 29 Feb 2024 • Sarah Müller, Lisa M. Koch, Hendrik P. A. Lensch, Philipp Berens
Retinal fundus images play a crucial role in the early detection of eye diseases and, using deep learning approaches, recent studies have even demonstrated their potential for detecting cardiovascular risk factors and neurological disorders.
no code implementations • 18 Jan 2024 • Andreas Engelhardt, Amit Raj, Mark Boss, Yunzhi Zhang, Abhishek Kar, Yuanzhen Li, Deqing Sun, Ricardo Martin Brualla, Jonathan T. Barron, Hendrik P. A. Lensch, Varun Jampani
We present SHINOBI, an end-to-end framework for the reconstruction of shape, material, and illumination from object images captured with varying lighting, pose, and background.
1 code implementation • 8 Nov 2023 • Leonard Salewski, A. Sophia Koepke, Hendrik P. A. Lensch, Zeynep Akata
Converting a model's internals to text can yield human-understandable insights about the model.
2 code implementations • 16 Oct 2023 • Hassan Shahmohammadi, Adhiraj Ghosh, Hendrik P. A. Lensch
Figurative and non-literal expressions are profoundly integrated in human communication.
1 code implementation • 14 Jul 2023 • Simon Holdenried-Krafft, Peter Somers, Ivonne A. Montes-Majarro, Diana Silimon, Cristina Tarín, Falko Fend, Hendrik P. A. Lensch
With our work, we explore the potential of dynamic meta-embedding based on cutting-edge self-supervised pre-trained models in the context of MIL.
no code implementations • 30 Jun 2023 • Simon Doll, Niklas Hanselmann, Lukas Schneider, Richard Schulz, Markus Enzweiler, Hendrik P. A. Lensch
Following the tracking-by-attention paradigm, this paper introduces an object-centric, transformer-based framework for tracking in 3D.
no code implementations • 8 Sep 2022 • Wafaa Mohammed, Hassan Shahmohammadi, Hendrik P. A. Lensch, R. Harald Baayen
We obtained visually grounded vector representations for these languages and studied whether visual grounding on one or multiple languages improved the performance of embeddings on word similarity and categorization benchmarks.
1 code implementation • 19 Aug 2022 • Zohreh Ghaderi, Leonard Salewski, Hendrik P. A. Lensch
To generate proper captions for videos, the inference needs to identify relevant concepts and pay attention to the spatial relationships between them as well as to the temporal development in the clip.
Ranked #7 on Video Captioning on VATEX
no code implementations • 30 Jun 2022 • Hassan Shahmohammadi, Maria Heitmeier, Elnaz Shafaei-Bajestan, Hendrik P. A. Lensch, Harald Baayen
To what extent does this setup rely on visual information from images?
1 code implementation • 17 Jun 2022 • Hassan Shahmohammadi, Maria Heitmeier, Elnaz Shafaei-Bajestan, Hendrik P. A. Lensch, Harald Baayen
Our model effectively balances the interplay between language and vision by aligning textual embeddings with visual information while simultaneously preserving the distributional statistics that characterize word usage in text corpora.
1 code implementation • 31 May 2022 • Mark Boss, Andreas Engelhardt, Abhishek Kar, Yuanzhen Li, Deqing Sun, Jonathan T. Barron, Hendrik P. A. Lensch, Varun Jampani
Our method works on in-the-wild online image collections of an object and produces relightable 3D assets for several use-cases such as AR/VR.
1 code implementation • 5 Apr 2022 • Leonard Salewski, A. Sophia Koepke, Hendrik P. A. Lensch, Zeynep Akata
We present baseline results for generating natural language explanations in the context of VQA using two state-of-the-art frameworks on the CLEVR-X dataset.
Ranked #1 on Explanation Generation on CLEVR-X
1 code implementation • NeurIPS 2021 • Mark Boss, Varun Jampani, Raphael Braun, Ce Liu, Jonathan T. Barron, Hendrik P. A. Lensch
Decomposing a scene into its shape, reflectance and illumination is a fundamental problem in computer vision and graphics.
1 code implementation • CoNLL (EMNLP) 2021 • Hassan Shahmohammadi, Hendrik P. A. Lensch, R. Harald Baayen
The general approach is to embed both textual and visual information into a common space -the grounded space-confined by an explicit relationship between both modalities.
1 code implementation • ICCV 2021 • Mark Boss, Raphael Braun, Varun Jampani, Jonathan T. Barron, Ce Liu, Hendrik P. A. Lensch
This problem is inherently more challenging when the illumination is not a single light source under laboratory conditions but is instead an unconstrained environmental illumination.
Ranked #5 on Image Relighting on Stanford-ORB
no code implementations • 21 Sep 2020 • Matthias Karlbauer, Tobias Menge, Sebastian Otte, Hendrik P. A. Lensch, Thomas Scholten, Volker Wulfmeyer, Martin V. Butz
Knowledge about the hidden factors that determine particular system dynamics is crucial for both explaining them and pursuing goal-directed interventions.
no code implementations • 19 Sep 2020 • Matthias Karlbauer, Sebastian Otte, Hendrik P. A. Lensch, Thomas Scholten, Volker Wulfmeyer, Martin V. Butz
The novel DISTributed Artificial neural Network Architecture (DISTANA) is a generative, recurrent graph convolution neural network.
1 code implementation • CVPR 2020 • Mark Boss, Varun Jampani, Kihwan Kim, Hendrik P. A. Lensch, Jan Kautz
Extensive experiments on both synthetic and real-world datasets show that our network trained on a synthetic dataset can generalize well to real-world images.
1 code implementation • 23 Dec 2019 • Matthias Karlbauer, Sebastian Otte, Hendrik P. A. Lensch, Thomas Scholten, Volker Wulfmeyer, Martin V. Butz
We introduce a distributed spatio-temporal artificial neural network architecture (DISTANA).
1 code implementation • 2 Dec 2019 • Fabian Groh, Lukas Ruppert, Patrick Wieschollek, Hendrik P. A. Lensch
Approximate nearest neighbor (ANN) search in high dimensions is an integral part of several computer vision systems and gains importance in deep learning with explicit memory representations.
no code implementations • 11 Oct 2019 • Mark Boss, Hendrik P. A. Lensch
Creating plausible surfaces is an essential component in achieving a high degree of realism in rendering.
1 code implementation • 20 Mar 2018 • Fabian Groh, Patrick Wieschollek, Hendrik P. A. Lensch
Traditional convolution layers are specifically designed to exploit the natural data representation of images -- a fixed and regular grid.
1 code implementation • ICCV 2017 • Patrick Wieschollek, Michael Hirsch, Bernhard Schölkopf, Hendrik P. A. Lensch
As handheld video cameras are now commonplace and available in every smartphone, images and videos can be recorded almost everywhere at anytime.
1 code implementation • CVPR 2016 • Patrick Wieschollek, Oliver Wang, Alexander Sorkine-Hornung, Hendrik P. A. Lensch
We present a new approach for efficient approximate nearest neighbor (ANN) search in high dimensional spaces, extending the idea of Product Quantization.
no code implementations • 8 Feb 2017 • Patrick Wieschollek, Fabian Groh, Hendrik P. A. Lensch
Fisher-Vectors (FV) encode higher-order statistics of a set of multiple local descriptors like SIFT features.
2 code implementations • 16 Nov 2016 • Katharina Schwarz, Patrick Wieschollek, Hendrik P. A. Lensch
Rating how aesthetically pleasing an image appears is a highly complex matter and depends on a large number of different visual factors.
no code implementations • 19 Oct 2016 • Patrick Wieschollek, Ido Freeman, Hendrik P. A. Lensch
Aligning video sequences is a fundamental yet still unsolved component for a broad range of applications in computer graphics and vision.
no code implementations • 20 Sep 2016 • Patrick Wieschollek, Hendrik P. A. Lensch
Specifically, transfer learning from the task of object recognition is exploited to more effectively train good features for material classification.
no code implementations • 15 Jul 2016 • Patrick Wieschollek, Bernhard Schölkopf, Hendrik P. A. Lensch, Michael Hirsch
We present a neural network model approach for multi-frame blind deconvolution.
no code implementations • 31 May 2016 • Matthias Limmer, Julian Forster, Dennis Baudach, Florian Schüle, Roland Schweiger, Hendrik P. A. Lensch
The proposed approach reliably detects roads with and without lane markings and thus increases the robustness and availability of road course estimations and augmented reality navigation.
2 code implementations • 8 Apr 2016 • Matthias Limmer, Hendrik P. A. Lensch
This paper proposes a method for transferring the RGB color spectrum to near-infrared (NIR) images using deep multi-scale convolutional neural networks.
no code implementations • CVPR 2015 • Benjamin Resch, Hendrik P. A. Lensch, Oliver Wang, Marc Pollefeys, Alexander Sorkine-Hornung
Videos consisting of thousands of high resolution frames are challenging for existing structure from motion (SfM) and simultaneous-localization and mapping (SLAM) techniques.