Dmytro Bobkov

Dmytro Bobkov

Auto-generated profile, based on publicly available information

Dmytro Bobkov

Chair of Media Technology, Technical University of Munich, Munich, Germany

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
29 August 2019 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
ZJZhi Jin
Zhi Jin
MIMuhammad Zafar Iqbal
Muhammad Zafar Iqbal
DBDmytro Bobkov
Dmytro Bobkov
WZWenbin Zou
Wenbin Zou
XLXia Li
Xia Li
ESEckehard Steinbach
Eckehard Steinbach
Image restoration is a long-standing problem in image processing and low-level computer vision. Recently, discriminative convolutional neural network (CNN)-based approaches have attracted considerable attention due to their superior performance. However, most of these frameworks are designed for one specific image restoration task; hence, they seldom show high performance on other image restoration tasks. To address this issue, we propose a flexible deep CNN framework that exploits the frequency characteristics of different types of artifacts. Hence, the same approach can be employed for a variety of image restoration tasks by adjusting the architecture. For reducing the artifacts with similar frequency characteristics, a quality enhancement network that adopts residual and recursive learning is proposed. Residual learning is utilized to speed up the training process and boost the performance; recursive learning is adopted to significantly reduce the number of training parameters as well as boost the performance. Moreover, lateral connections transmit the extracted features between different frequency streams via multiple paths. One aggregation network combines the outputs of these streams to further enhance the restored images. We demonstrate the capabilities of the proposed framework with three representative applications: image compression artifacts reduction (CAR), image denoising, and single image super-resolution (SISR). Extensive experiments confirm that the proposed framework outperforms the state-of-the-art approaches on benchmark datasets for these applications.

9 January 2019 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
LHLei Han
Lei Han
LXLan Xu
Lan Xu
DBDmytro Bobkov
Dmytro Bobkov
ESEckehard Steinbach
Eckehard Steinbach
LFLu Fang
Lu Fang

12 January 2018 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
DBDmytro Bobkov
Dmytro Bobkov
SCSili Chen
Sili Chen
RJRuiqing Jian
Ruiqing Jian
MIMuhammad Z. Iqbal
Muhammad Z. Iqbal
ESEckehard Steinbach
Eckehard Steinbach
Object retrieval and classification in point cloud data are challenged by noise, irregular sampling density, and occlusion. To address this issue, we propose a point pair descriptor that is robust to noise and occlusion and achieves high retrieval accuracy. We further show how the proposed descriptor can be used in a four-dimensional (4-D) convolutional neural network for the task of object classification. We propose a novel 4-D convolutional layer that is able to learn class-specific clusters in the descriptor histograms. Finally, we provide experimental validation on three benchmark datasets, which confirms the superiority of the proposed approach.

1 July 2017
Verified
Conference Paper
Closed access
DBDmytro Bobkov
Dmytro Bobkov
MKMartin Kiechle
Martin Kiechle
SHSebastian Hilsenbeck
Sebastian Hilsenbeck
ESEckehard Steinbach
Eckehard Steinbach
Emerging applications, such as indoor navigation or facility management, present new requirements of automatic and robust partitioning of indoor 3D point clouds into rooms. Previous research is either based on the Manhattan-world assumption or relies on the availability of the scanner pose information. We address these limitations by following the architectural definition of a room, where the room is an inner free space separated from other spaces through openings or partitions. For this we formulate an anisotropic potential field for 3D environments and illustrate how it can be used for room segmentation in the proposed segmentation pipeline. The experimental results confirm that our method outperforms state-of-the-art methods on a number of datasets including those that violate the Manhattan-world assumption.