Pattern Recognition
45th DAGM German Conference, DAGM GCPR 2023, Heidelberg, Germany, September 19–22, 2023, Proceedings
Book and Conference Proceedings
45th DAGM German Conference, DAGM GCPR 2023, Heidelberg, Germany, September 19–22, 2023, Proceedings
Article
Article
In this work, we focus on outdoor lighting estimation by aggregating individual noisy estimates from images, exploiting the rich image information from wide-angle cameras and/or temporal image sequences. Photo...
Chapter and Conference Paper
The graph matching optimization problem is an essential component for many tasks in computer vision, such as bringing two deformable objects in correspondence. Naturally, a wide range of applicable algorithms ...
Article
When designing a semantic segmentation model for a real-world application, such as autonomous driving, it is crucial to understand the robustness of the network with respect to a wide range of image corruption...
Chapter and Conference Paper
Multispectral photoacoustic imaging (PAI) is an emerging imaging modality that enables the recovery of functional tissue parameters such as blood oxygenation. However, the underlying inverse reconstruction pro...
Chapter and Conference Paper
We introduce a new architecture called a conditional invertible neural network (cINN), and use it to address the task of diverse image-to-image translation for natural images. This is not easily possible with ...
Chapter and Conference Paper
Standard supervised learning breaks down under data distribution shift. However, the principle of independent causal mechanisms (ICM, [31]) can turn this weakness into an opportunity: one can take advantage of di...
Chapter and Conference Paper
In this work, we focus on outdoor lighting estimation by aggregating individual noisy estimates from images, exploiting the rich image information from wide-angle cameras and/or temporal image sequences. Photo...
Chapter and Conference Paper
For safety-critical applications such as autonomous driving, CNNs have to be robust with respect to unavoidable image corruptions, such as image noise. While previous works addressed the task of robust predict...
Chapter and Conference Paper
This paper presents the evaluation methodology, datasets, and results of the BOP Challenge 2020, the third in a series of public competitions organized with the goal to capture the status quo in the field of 6...
Article
Optical imaging is evolving as a key technique for advanced sensing in the operating room. Recent research has shown that machine learning algorithms can be used to address the inverse problem of converting pi...
Chapter and Conference Paper
Multispectral optical imaging is becoming a key tool in the operating room. Recent research has shown that machine learning algorithms can be used to convert pixel-wise reflectance measurements to tissue para...
Chapter and Conference Paper
This document summarizes the 4th International Workshop on Recovering 6D Object Pose which was organized in conjunction with ECCV 2018 in Munich. The workshop featured four invited talks, oral and poster prese...
Chapter and Conference Paper
We address the task of 6D pose estimation of known rigid objects from single input images in scenarios where the objects are partly occluded. Recent RGB-D-based methods are robust to moderate degrees of occlus...
Chapter and Conference Paper
This work presents a deep object co-segmentation (DOCS) approach for segmenting common objects of the same class within a pair of images. This means that the method learns to ignore common, or uncommon, backgr...
Chapter and Conference Paper
The task of generating natural images from 3D scenes has been a long standing goal in computer graphics. On the other hand, recent developments in deep neural networks allow for trainable models that can produ...
Article
The success of deep learning in computer vision is based on the availability of large annotated datasets. To lower the need for hand labeled images, virtually rendered 3D worlds have recently gained popularity...
Chapter and Conference Paper
We propose a benchmark for 6D pose estimation of a rigid object from a single RGB-D input image. The training data consists of a texture-mapped 3D object model or images of the object in known 6D poses. The be...
Chapter and Conference Paper
Dense, discrete Graphical Models with pairwise potentials are a powerful class of models which are employed in state-of-the-art computer vision and bio-imaging applications. This work introduces a new MAP-solv...