Our team is present at the European Conference on Computer Vision (ECCV) 2020 with two workshop papers! Both will be presented on Friday 28th August.
The first “Deep Cyclic Generative Adversarial Residual Convolutional Networks for Real Image Super-Resolution”, by Rao Muhammad Umer and Christian Micheloni, will be presented at the Advances in Image Manipulation Workshop and Challenges (AIM 2020). In the following you can find abstract and spotlight video.
Recent deep learning based single image super-resolution (SISR) methods mostly train their models in a clean data domain where the low-resolution (LR) and the high-resolution (HR) images come from noise-free settings (same domain) due to the bicubic down-sampling assumption. However, such degradation process is not available in real-world settings. We consider a deep cyclic network structure to maintain the domain consistency between the LR and HR data distributions, which is inspired by the recent success of CycleGAN in the image-to-image translation applications. We propose the Super-Resolution Residual Cyclic Generative Adversarial Network (SRResCycGAN) by training with a generative adversarial network (GAN) framework for the LR to HR domain translation in an end-to-end manner. We demonstrate our proposed approach in the quantitative and qualitative experiments that generalize well to the real image super-resolution and it is easy to deploy for the mobile/embedded devices. In addition, our SR results on the AIM 2020 Real Image SR Challenge datasets demonstrate that the proposed SR approach achieves comparable results as the other state-of-art methods.
The second paper “An Exploration of Target-Conditioned Segmentation Methods for Visual Object Trackers”, by Matteo Dunnhofer, Niki Martinel, and Christian Micheloni, will be presented at the Visual Object Tracking Challenge VOT2020 workshop. Again, here you can find abstract and teaser video.
Visual object tracking is the problem of predicting a target object’s state in a video. Generally, bounding-boxes have been used to represent states, and a surge of effort has been spent by the community to produce efficient causal algorithms capable of locating targets with such representations. As the field is moving towards binary segmentation masks to define objects more precisely, in this paper we propose to extensively explore target-conditioned segmentation methods available in the computer vision community, in order to transform any bounding-box tracker into a segmentation tracker. Our analysis shows that such methods allow trackers to compete with recently proposed segmentation trackers, while performing quasi real-time.