Publications associées à Using A Priori Knowledge to Improve Scene Understanding

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance

Devis Tuia, Valérie Zermatten, Javiera Francisca Castillo Navarro, Xiaolong Lu

Deep learning has emerged as a promising avenue for automatic mapping, demonstrating high efficacy in land cover categorization through various semantic segmentation models. Nonetheless, the practical deployment of these models encounters important challen ...

Ieee-Inst Electrical Electronics Engineers Inc2024

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

Evann Pierre Guy Courdier

Deep learning has revolutionized the field of computer vision, a success largely attributable to the growing size of models, datasets, and computational power. Simultaneously, a critical pain point arises as several computer vision applications are deploye ...

EPFL2024

Aggregating Spatial and Photometric Context for Photometric Stereo

David Honzátko

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

EPFL2024

Dynamic Voxels Based on Ego-Conditioned Prediction: An Integrated Spatio-Temporal Framework for Motion Planning

Alexandre Massoud Alahi, Ting Zhang

Prediction is a vital component of motion planning for autonomous vehicles (AVs). By reasoning about the possible behavior of other target agents, the ego vehicle (EV) can navigate safely, efficiently, and politely. However, most of the existing work overl ...

IEEE Institute of Electrical and Electronics Engineers2024

Text as a Richer Source of Supervision in Semantic Segmentation Tasks

Devis Tuia, Valérie Zermatten, Lloyd Haydn Hughes, Javiera Francisca Castillo Navarro

This paper introduces TACOSS a text-image alignment approach that allows explainable land cover semantic segmentation by directly integrating semantic concepts encoded from texts. TACOSS combines convolutional neural networks for visual feature extraction ...

The Institute of Electrical and Electronics Engineers, Inc2023

Detecting Anomalies and Obstacles in Road Scenes

Krzysztof Maciej Lis

We address the problem of segmenting anomalies and unusual obstacles in road scenes for the purpose of self-driving safety. The objects in question are not present in the common training sets as it is not feasible to collect and annotate examples for every ...

EPFL2023

Chaotic microcomb inertia-free parallel ranging

Tobias Kippenberg, Anton Stroganov, Anton Lukashchuk

Ever growing pixel acquisition rates in the fields of augmented reality, autonomous driving and robotics have increased interest in solid state beam scanning without moving parts. Modern photonic integrated laser ranging advances towards passive beam steer ...

AIP Publishing2023

Deep Generative Models for Autonomous Driving: from Motion Forecasting to Realistic Image Synthesis

Saeed Saadatnejad

Forecasting is a capability inherent in humans when navigating. Humans routinely plan their paths, considering the potential future movements of those around them. Similarly, to achieve comparable sophistication and safety, autonomous systems must embrace ...

EPFL2023

Haptics based collaborative steering control in automated driving environments

Tomohiro Nakade

A vehicle's steering is a particular system in that it is exposed to individual subjective reviews based on criteria that are hard to assess quantitatively. Haptic design of such systems is a prime concern that has been at the center of industrial developm ...

EPFL2023

Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union

Devis Tuia, Zifu Wang

Semantic segmentation datasets often exhibit two types of imbalance: \textit{class imbalance}, where some classes appear more frequently than others and \textit{size imbalance}, where some objects occupy more pixels than others. This causes traditional eva ...

2023

Haptics based multi-level collaborative steering control for automated driving

Robert Fuchs, Jürg Alexander Schiffmann, Hannes Bleuler, Tomohiro Nakade

Increasing the capability of automated driving vehicles is motivated by environmental, productivity, and traffic safety benefits. But over-reliance on the automation system is known to cause accidents. The role of the driver cannot be underestimated as it ...

2023

An end-to-end pipeline for historical censuses processing

Marion Kramer, Rémi Guillaume Petitpierre, Lucas Arnaud André Rappo

Censuses are structured documents of great value for social and demographic history, which became widespread from the nineteenth century on. However, the plurality of formats and the natural variability of historical data make their extraction arduous and ...

2023

Affordance segmentation of hand-occluded containers from exocentric images

Andrea Cavallaro

Visual affordance segmentation identifies the surfaces of an object an agent can interact with. Common challenges for the identification of affordances are the variety of the geometry and physical properties of these surfaces as well as occlusions. In this ...

Ieee Computer Soc2023

Object-oriented modelling of advanced computer cooling solutions

David Atienza Alonso, Federico Terraneo

Modern computing systems are so energy- intensive to make efficient cooling vital for their operation. This is giving rise to a variety of innovative cooling solutions based on a mix of traditional and new techniques. The design and engineering of these so ...

Elsevier2023

Localized model order reduction and domain decomposition methods for coupled heterogeneous systems

Jan Sickmann Hesthaven, Niccolo' Discacciati

We propose a model order reduction technique to accurately approximate the behavior of multi-component systems without any a-priori knowledge of the coupled model. In the offline phase, we construct independent surrogate models by solving the local problem ...

Wiley2023

Confidence Matters: Applications to Semantic Segmentation

Prabhu Teja Sivaprasad

The successes of deep learning for semantic segmentation can in be, in part, attributed to its scale: a notion that encapsulates the largeness of these computational architectures and the labeled datasets they are trained on. These resource requirements hi ...

EPFL2023

Cross-resolution Face Recognition via Identity-Preserving Network and Knowledge Distillation

Touradj Ebrahimi, Yuhang Lu

Cross-resolution face recognition has become a challenging problem for modern deep face recognition systems. It aims at matching a low-resolution probe image with high-resolution gallery images registered in a database. Existing methods mainly leverage pri ...

2023

Encoder-Decoder Models for Human Segmentation and Motion Analysis

Isinsu Katircioglu

Detecting people from 2D images and analyzing their motion in 3D have been long standing computer vision problems central to numerous applications such as autonomous driving and athletic training. Recently, with the availability of large amounts of trainin ...

EPFL2022

Reshaping Perception for Autonomous Driving with Semantic Keypoints

Lorenzo Bertoni

The field of artificial intelligence is set to fuel the future of mobility by driving forward the transition from advanced driver-assist systems to fully autonomous vehicles (AV). Yet the current technology, backed by cutting-edge deep learning techniques, ...

EPFL2022

Pedestrian 3D Bounding Box Prediction

Alexandre Massoud Alahi, Saeed Saadatnejad, Yi Zhou Ju

Safety is still the main issue of autonomous driving, and in order to be globally deployed, they need to predict pedestrians' motions sufficiently in advance. While there is a lot of research on coarse-grained (human center prediction) and fine-grained pre ...

2022