Givi Meishvili

Givi Meishvili
Universität Bern | UniBe · Institute of Computer Science and Applied Mathematics

About

11
Publications
736
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
152
Citations

Publications

Publications (11)
Article
Optimization is often cast as a deterministic problem, where the solution is found through some iterative procedure such as gradient descent. However, when training neural networks the loss function changes over (iteration) time due to the randomized selection of a subset of the samples. This randomization turns the optimization problem into a stoc...
Preprint
We propose a solution to the novel task of rendering sharp videos from new viewpoints from a single motion-blurred image of a face. Our method handles the complexity of face blur by implicitly learning the geometry and motion of faces through the joint training on three large datasets: FFHQ and 300VW, which are publicly available, and a new Bern Mu...
Conference Paper
Full-text available
We propose a solution to the novel task of rendering sharp videos from new viewpoints from a single motion-blurred image of a face. Our method 1 handles the complexity of face blur by implicitly learning the geometry and motion of faces through the joint training on three large datasets: FFHQ and 300VW, which are publicly available, and a new Bern...
Preprint
Full-text available
Optimization is often cast as a deterministic problem, where the solution is found through some iterative procedure such as gradient descent. However, when training neural networks the loss function changes over (iteration) time due to the randomized selection of a subset of the samples. This randomization turns the optimization problem into a stoc...
Chapter
We introduce a novel self-supervised learning approach to learn representations of videos that are responsive to changes in the motion dynamics. Our representations can be learned from data without human annotation and provide a substantial boost to the training of neural networks on small labeled data sets for tasks such as action recognition, whi...
Preprint
Full-text available
We introduce a novel self-supervised learning approach to learn representations of videos that are responsive to changes in the motion dynamics. Our representations can be learned from data without human annotation and provide a substantial boost to the training of neural networks on small labeled data sets for tasks such as action recognition, whi...
Preprint
In this paper we present, to the best of our knowledge, the first method to learn a generative model of 3D shapes from natural images in a fully unsupervised way. For example, we do not use any ground truth 3D or 2D annotations, stereo video, and ego-motion during the training. Our approach follows the general strategy of Generative Adversarial Net...
Preprint
We propose a novel method to use both audio and a low-resolution image to perform extreme face super-resolution (a 16× increase of the input size). When the resolution of the input image is very low (e.g., 8 × 8 pixels), the loss of information is so dire that important details of the original identity have been lost and audio can aid the recovery...
Article
We present a method to extract a video sequence from a single motion-blurred image. Motion-blurred images are the result of an averaging process, where instant frames are accumulated over time during the exposure of the sensor. Unfortunately, reversing this process is nontrivial. Firstly, averaging destroys the temporal ordering of the frames. Seco...