801 citations · 1.1k across the 20 of their papers we have counts for
27 papers
GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering
Zinuo You, Stamatios Georgoulis, Anpei Chen +2
Video stabilization is pivotal for video processing, as it removes unwanted shakiness while preserving the original user motion intent. Existing approaches, depending on the domain…
Out of the Room: Generalizing Event-Based Dynamic Motion Segmentation for Complex Scenes
Stamatios Georgoulis, Weining Ren, Alfredo Bochicchio +3
Rapid and reliable identification of dynamic scene parts, also known as motion segmentation, is a key challenge for mobile sensors. Contemporary RGB camera-based methods rely on mo…
Event-based Image Deblurring with Dynamic Motion Awareness
Patricia Vitoria, Stamatios Georgoulis, Stepan Tulyakov +3
Non-uniform image deblurring is a challenging task due to the lack of temporal and textural information in the blurry image itself. Complementary information from auxiliary sensors…
Multi-Bracket High Dynamic Range Imaging with Event Cameras
Nico Messikommer, Stamatios Georgoulis, Daniel Gehrig +5
Modern high dynamic range (HDR) imaging pipelines align and fuse multiple low dynamic range (LDR) images captured at different exposure times. While these methods work well in stat…
Time Lens++: Event-based Frame Interpolation with Parametric Non-linear Flow and Multi-scale Fusion
Stepan Tulyakov, Alfredo Bochicchio, Daniel Gehrig +3
Recently, video frame interpolation using a combination of frame- and event-based cameras has surpassed traditional image-based methods both in terms of performance and memory effi…
FoV-Net: Field-of-View Extrapolation Using Self-Attention and Uncertainty
Liqian Ma, Stamatios Georgoulis, Xu Jia +1
The ability to make educated predictions about their surroundings, and associate them with certain confidence, is important for intelligent systems, like autonomous vehicles and ro…
TimeLens: Event-based Video Frame Interpolation
Stepan Tulyakov, Daniel Gehrig, Stamatios Georgoulis +4
State-of-the-art frame interpolation methods generate intermediate frames by inferring object motions in the image from consecutive key-frames. In the absence of additional informa…
Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations
Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis +1
Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still pri…
Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation
Suman Saha, Anton Obukhov, Danda Pani Paudel +4
We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. Semantic segmentation and monocular d…
Exploring Relational Context for Multi-Task Dense Prediction
David Bruggemann, Menelaos Kanakis, Anton Obukhov +2
The timeline of computer vision research is marked with advances in learning and utilizing efficient contextual representations. Most of them, however, are targeted at improving mo…
Spectral Tensor Train Parameterization of Deep Learning Layers
Anton Obukhov, Maxim Rakhuba, Alexander Liniger +4
We study low-rank parameterizations of weight matrices with embedded spectral properties in the Deep Learning context. The low-rank property leads to parameter efficiency and permi…
Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals
Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis +1
Being able to learn dense semantic representations of images without supervision is an important problem in computer vision. However, despite its significance, this problem remains…
Automated Search for Resource-Efficient Branched Multi-Task Networks
David Bruggemann, Menelaos Kanakis, Stamatios Georgoulis +1
The multi-modal nature of many vision problems calls for neural network architectures that can perform multiple tasks concurrently. Typically, such architectures have been handcraf…
Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference
Menelaos Kanakis, David Bruggemann, Suman Saha +3
Multi-task networks are commonly utilized to alleviate the need for a large number of highly specialized single-task networks. However, two common challenges in developing multi-ta…
T-Basis: a Compact Representation for Neural Networks
Anton Obukhov, Maxim Rakhuba, Stamatios Georgoulis +3
We introduce T-Basis, a novel concept for a compact representation of a set of tensors, each of an arbitrary shape, which is often seen in Neural Networks. Each of the tensors in t…
SCAN: Learning to Classify Images without Labels
Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis +2
Can we automatically group images into semantically meaningful clusters when ground-truth annotations are absent? The task of unsupervised image classification remains an important…
Multi-Task Learning for Dense Prediction Tasks: A Survey
Simon Vandenhende, Stamatios Georgoulis, Wouter Van Gansbeke +3
With the advent of deep learning, many dense prediction tasks, i.e. tasks that produce pixel-level predictions, have seen significant performance improvements. The typical approach…
MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning
Simon Vandenhende, Stamatios Georgoulis, Luc Van Gool
In this paper, we argue about the importance of considering task interactions at multiple scales when distilling task information in a multi-task learning setup. In contrast to com…
Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing
Suman Saha, Wenhao Xu, Menelaos Kanakis +4
Nowadays, the increasingly growing number of mobile and computing devices has led to a demand for safer user authentication systems. Face anti-spoofing is a measure towards this di…
Gated CRF Loss for Weakly Supervised Semantic Image Segmentation
Anton Obukhov, Stamatios Georgoulis, Dengxin Dai +1
State-of-the-art approaches for semantic segmentation rely on deep convolutional neural networks trained on fully annotated datasets, that have been shown to be notoriously expensi…
Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency
Liqian Ma, Xu Jia, Stamatios Georgoulis +2
Image-to-image translation has recently received significant attention due to advances in deep learning. Most works focus on learning either a one-to-one mapping in an unsupervised…
Towards End-to-End Lane Detection: an Instance Segmentation Approach
Davy Neven, Bert De Brabandere, Stamatios Georgoulis +2
Modern cars are incorporating an increasing number of driver assist features, among which automatic lane keeping. The latter allows the car to properly position itself within the r…
Error Correction for Dense Semantic Image Labeling
Yu-Hui Huang, Xu Jia, Stamatios Georgoulis +2
Pixelwise semantic image labeling is an important, yet challenging, task with many applications. Typical approaches to tackle this problem involve either the training of deep netwo…
Disentangled Person Image Generation
Liqian Ma, Qianru Sun, Stamatios Georgoulis +3
Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and po…