A Shared Representation for Photorealistic Driving Simulators

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

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 ...

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 ...

Video DeepFakes are fake media created with Deep Learning (DL) that manipulate a person’s expression or identity. Most current DeepFake detection methods analyze each frame independently, ignoring inconsistencies and unnatural movements between frames. Som ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

The present work proposes a framework for nonlinear model order reduction based on a Graph Convolutional Autoencoder (GCA-ROM). In the reduced order modeling (ROM) context, one is interested in obtaining real -time and many-query evaluations of parametric ...

Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...

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 ...

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 ...

The application of unsupervised domain adaptation (UDA)-based fault diagnosis methods has shown significant efficacy in industrial settings, facilitating the transfer of operational experience and fault signatures between different operating conditions, di ...

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 ...

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 ...

Most recent test-time adaptation methods focus on only classification tasks, use specialized network architectures, destroy model calibration or rely on lightweight information from the source domain. To tackle these issues, this paper proposes a novel Tes ...

While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet. The key idea of recent works to ...

Characterizing the genetic structure of large cohorts has become increasingly important as genetic studies extend to massive, increasingly diverse biobanks. Popular methods decompose individual genomes into fractional cluster assignments with each cluster ...

Recently, it has been exposed that some modern facial recognition systems could discriminate specific demographic groups and may lead to unfair attention with respect to various facial attributes such as gender and origin. The main reason are the biases in ...

Current Dynamic Texture Synthesis (DyTS) models can synthesize realistic videos. However, they require a slow iterative optimization process to synthesize a single fixed-size short video, and they do not offer any post-training control over the synthesis p ...

Learning-based outlier (mismatched correspondence) rejection for robust 3D registration generally formulates the outlier removal as an inlier/outlier classification problem. The core for this to be successful is to learn the discriminative inlier/outlier f ...

Pulmonary nodules and masses are crucial imaging features in lung cancer screening that require careful management in clinical diagnosis. Despite the success of deep learning-based medical image segmentation, the robust performance on various sizes of lesi ...

A Shared Representation for Photorealistic Driving Simulators

Chat with Graph Search

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance

Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

A graph convolutional autoencoder approach to model order reduction for parametrized PDEs

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Aggregating Spatial and Photometric Context for Photometric Stereo

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

Smart filter aided domain adversarial neural network for fault diagnosis in noisy industrial scenarios

Learnable Wavelet Transform and Domain Adversarial Learning for Enhanced Bearing Fault Diagnosis

Text as a Richer Source of Supervision in Semantic Segmentation Tasks

Detecting Anomalies and Obstacles in Road Scenes

TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation

Fast Adversarial Training With Adaptive Step Size

Neural ADMIXTURE for rapid genomic clustering

Toward responsible face datasets: modeling the distribution of a disentangled latent space for sampling face images from demographic groups

DyNCA: Real-time Dynamic Texture Synthesis Using Neural Cellular Automata

Robust Outlier Rejection for 3D Registration with Variational Bayes

Scale-Aware Test-Time Click Adaptation for Pulmonary Nodule and Mass Segmentation