AIConfPaper
← Search

Stamatios Georgoulis

16 accepted papers

2022

Time Lens++: Event-Based Frame Interpolation With Parametric Non-Linear Flow and Multi-Scale Fusion

Stepan Tulyakov, Alfredo Bochicchio, Daniel Gehrig, Stamatios Georgoulis, Yuanyou Li, Davide Scaramuzza
CVPR 2022poster

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 efficiency. However, current methods still suffer from (i) brittle image-level fusion of complementary interpolation results…

Cited by 149PDF ↗Scholar ↗
2021

Exploring Relational Context for Multi-Task Dense Prediction

David Brüggemann, Menelaos Kanakis, Anton Obukhov, Stamatios Georgoulis, Luc Van Gool
ICCV 2021poster

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 model performance on a single downstream task. We consider a multi-task environment for dense prediction tasks, represente…

Cited by 97PDF ↗code ↗Scholar ↗
2021

FoV-Net: Field-of-View Extrapolation Using Self-Attention and Uncertainty

Liqian Ma, Stamatios Georgoulis, Xu Jia, Luc Van Gool
RA-L 2021

The ability to make educated predictions about their surroundings, and associate them with certain confidence, is important for intelligent systems, like autonomous vehicles and robots. It allows them to plan early and decide accordingly. Motivated by this observation, in this letter we utilize info

Cited by 7Source ↗code ↗Scholar ↗
2021

Learning To Relate Depth and Semantics for Unsupervised Domain Adaptation

Suman Saha, Anton Obukhov, Danda Pani Paudel, Menelaos Kanakis, Yuhua Chen, Stamatios Georgoulis +1
CVPR 2021poster

We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. Semantic segmentation and monocular depth estimation are shown to be complementary tasks; in a multi-task learning setting, a proper encoding of their relati…

Cited by 70PDF ↗code ↗Scholar ↗
2021

Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations

Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis, Luc Van Gool
NeurIPS 2021poster

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this paper, we first study how biases in the dataset affect existin…

Cited by 70Source ↗PDF ↗code ↗Scholar ↗
2021

Spectral Tensor Train Parameterization of Deep Learning Layers

Anton Obukhov, Maxim Rakhuba, Alexander Liniger, Zhiwu Huang, Stamatios Georgoulis, Dengxin Dai +1
AISTATS 2021poster

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 permits taking computational shortcuts when computing mappings. Spectral properties are often subject to constraints in optim…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2021

Time Lens: Event-Based Video Frame Interpolation

Stepan Tulyakov, Daniel Gehrig, Stamatios Georgoulis, Julius Erbach, Mathias Gehrig, Yuanyou Li +1
CVPR 2021poster

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 information, first-order approximations, i.e. optical flow, must be used, but this choice restricts the types of motions that c…

Cited by 234PDF ↗code ↗Scholar ↗
2021

Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals

Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis, Luc Van Gool
ICCV 2021poster

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 rather unexplored, with a few exceptions that considered unsupervised semantic segmentation on small-scale datasets wit…

Cited by 307PDF ↗code ↗Scholar ↗
2020

MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning

Simon Vandenhende, Stamatios Georgoulis, Luc Van Gool
ECCV 2020poster

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 common belief, we show that tasks with high affinity at a certain scale are not guaranteed to retain this behaviour at othe…

Cited by 312Source ↗PDF ↗code ↗Scholar ↗
2020

Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference

Menelaos Kanakis, David Bruggemann, Suman Saha, Stamatios Georgoulis, Anton Obukhov, Luc Van Gool
ECCV 2020poster

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-task models are often overlooked in literature. First, enabling the model to be inherently incremental, continuously incor…

Cited by 104Source ↗PDF ↗code ↗Scholar ↗
2020

SCAN: Learning to Classify Images without Labels

Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis, Marc Proesmans, Luc Van Gool
ECCV 2020poster

Can we automatically group images into semantically meaningful clusters when ground-truth annotations are absent? The task of unsupervised image classification remains an important, and open challenge in computer vision. Several recent approaches have tried to tackle this problem in an end-to-end fa…

Cited by 710Source ↗PDF ↗code ↗Scholar ↗
2020

T-Basis: a Compact Representation for Neural Networks

Anton Obukhov, Maxim Rakhuba, Stamatios Georgoulis, Menelaos Kanakis, Dengxin Dai, Luc Van Gool
ICML 2020poster

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 the set is modeled using Tensor Rings, though the concept applies to other Tensor Networks. Owing its name to the T-shape…

Cited by 30Source ↗PDF ↗code ↗Scholar ↗
2019

Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency

Liqian Ma, Xu Jia, Stamatios Georgoulis, Tinne Tuytelaars, Luc Van Gool
ICLR 2019poster

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 way or a many-to-many mapping in a supervised way. However, a more practical setting is many-to-many mapping in an unsu…

Cited by 165Source ↗PDF ↗Scholar ↗
2018

Disentangled Person Image Generation

Liqian Ma, Qianru Sun, Stamatios Georgoulis, Luc Van Gool, Bernt Schiele, Mario Fritz
CVPR 2018poster

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 pose information. In this work, we aim at generating such images based on a novel, two-stage reconstruction pipeline that…

Cited by 541Source ↗PDF ↗Scholar ↗
2017

What Is Around the Camera?

Stamatios Georgoulis, Konstantinos Rematas, Tobias Ritschel, Mario Fritz, Tinne Tuytelaars, Luc Van Gool
ICCV 2017poster

How much does a single image reveal about the environment it was taken in? In this paper, we investigate how much of that information can be retrieved from a foreground object, combined with the background (i.e. the visible part of the environment). Assuming it is not perfectly diffuse, the foregrou…

Cited by 58PDF ↗Scholar ↗
2015

A Gaussian Process Latent Variable Model for BRDF Inference

Stamatios Georgoulis, Vincent Vanweddingen, Marc Proesmans, Luc Van Gool
ICCV 2015poster

The problem of estimating a full BRDF from partial observations has already been studied using either parametric or non-parametric approaches. The goal in each case is to best match this sparse set of input measurements. In this paper we address the problem of inferring higher order reflectance info…

Cited by 13PDF ↗Scholar ↗