Andreas Spruck
YOU?
Author Swipe
View article: Joint Geometry and Attribute Upsampling of Point Clouds Using Frequency-Selective Models with Overlapped Support
Joint Geometry and Attribute Upsampling of Point Clouds Using Frequency-Selective Models with Overlapped Support Open
With the increasing demand of capturing our environment in three-dimensions for AR/ VR applications and autonomous driving among others, the importance of high-resolution point clouds rises. As the capturing process is a complex task, poin…
View article: Jointly Resampling and Reconstructing Corrupted Images for Image Classification using Frequency-Selective Mesh-to-Grid Resampling
Jointly Resampling and Reconstructing Corrupted Images for Image Classification using Frequency-Selective Mesh-to-Grid Resampling Open
Neural networks became the standard technique for image classification throughout the last years. They are extracting image features from a large number of images in a training phase. In a following test phase, the network is applied to th…
View article: Frequency-Selective Geometry Upsampling of Point Clouds
Frequency-Selective Geometry Upsampling of Point Clouds Open
The demand for high-resolution point clouds has increased throughout the last years. However, capturing high-resolution point clouds is expensive and thus, frequently replaced by upsampling of low-resolution data. Most state-of-the-art met…
View article: Increasing the Accuracy of a Neural Network Using Frequency Selective Mesh-to-Grid Resampling
Increasing the Accuracy of a Neural Network Using Frequency Selective Mesh-to-Grid Resampling Open
Neural networks are widely used for almost any task of recognizing image content. Even though much effort has been put into investigating efficient network architectures, optimizers, and training strategies, the influence of image interpol…
View article: Synthesizing Annotated Image and Video Data Using a Rendering-Based Pipeline for Improved License Plate Recognition
Synthesizing Annotated Image and Video Data Using a Rendering-Based Pipeline for Improved License Plate Recognition Open
An insufficient number of training samples is a common problem in neural network applications. While data augmentation methods require at least a minimum number of samples, we propose a novel, rendering-based pipeline for synthesizing anno…
View article: Motion-Adapted Three-Dimensional Frequency Selective Extrapolation
Motion-Adapted Three-Dimensional Frequency Selective Extrapolation Open
It has been shown, that high resolution images can be acquired using a low resolution sensor with non-regular sampling. Therefore, post-processing is necessary. In terms of video data, not only the spatial neighborhood can be used to assis…
View article: Forensic License Plate Recognition with Compression-Informed Transformers
Forensic License Plate Recognition with Compression-Informed Transformers Open
Forensic license plate recognition (FLPR) remains an open challenge in legal contexts such as criminal investigations, where unreadable license plates (LPs) need to be deciphered from highly compressed and/or low resolution footage, e.g., …
View article: Frequency-Selective Mesh-to-Mesh Resampling for Color Upsampling of Point Clouds
Frequency-Selective Mesh-to-Mesh Resampling for Color Upsampling of Point Clouds Open
With the increased use of virtual and augmented reality applications, the importance of point cloud data rises. High-quality capturing of point clouds is still expensive and thus, the need for point cloud super-resolution or point cloud up…
View article: 3D Rendering Framework for Data Augmentation in Optical Character Recognition : (Invited Paper)
3D Rendering Framework for Data Augmentation in Optical Character Recognition : (Invited Paper) Open
In this paper, we propose a data augmentation framework for Optical Character\nRecognition (OCR). The proposed framework is able to synthesize new viewing\nangles and illumination scenarios, effectively enriching any available OCR\ndataset…
View article: Frame Rate Up-Conversion Using Key Point Agnostic Frequency-Selective Mesh-to-Grid Resampling
Frame Rate Up-Conversion Using Key Point Agnostic Frequency-Selective Mesh-to-Grid Resampling Open
High frame rates are desired in many fields of application. As in many cases\nthe frame repetition rate of an already captured video has to be increased,\nframe rate up-conversion (FRUC) is of high interest. We conduct a motion\ncompensate…
View article: Quality Assurance of Weld Seams Using Laser Triangulation Imaging and Deep Neural Networks
Quality Assurance of Weld Seams Using Laser Triangulation Imaging and Deep Neural Networks Open
In this paper, a novel optical inspection system is presented that is directly suitable for Industry 4.0 and the implementation on IoT-devices controlling the manufacturing process. The proposed system is capable of distinguishing between …
View article: Proceedings of the 4th Summer School on Video Compression and Processing (SVCP) 2018
Proceedings of the 4th Summer School on Video Compression and Processing (SVCP) 2018 Open
Proceedings of the 4th Summer School on Video Compression and Processing (SVCP) 2018