Viewers of 360-degree videos are provided with both visual modality to characterize their surrounding views and audio modality to indicate the sound direction. Though both modalities are important for saliency prediction, little work has been done by joint ...
In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...
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 ...
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 ...
Neural decoding of the visual system is a subject of research interest, both to understand how the visual system works and to be able to use this knowledge in areas, such as computer vision or brain-computer interfaces. Spike-based decoding is often used, ...
Understanding visual complexity of urban environments may improve urban design strategies and limit visual pollution due to advertising, road signage, telecommunication systems and machinery. This paper aims at quantifying visual complexity specifically in ...
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 ...
Single-photon avalanche diodes (SPADs) are novel image sensors that record the arrival of individual photons at extremely high temporal resolution. In the past, they were only available as single pixels or small-format arrays, for various active imaging ap ...
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 ...
Taking advantage of Capella's ability to dwell on a target for an extended period of time (nominally 30s) in its spotlight (SP) mode, an unsupervised methodology for detecting moving targets in this data is presented in this paper. By colourizing short seg ...
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 ...
Systematic compositionality, or the ability to adapt to novel situations by creating a mental model of the world using reusable pieces of knowledge, remains a significant challenge in machine learning. While there has been considerable progress in the lang ...
The principle of tailoring material properties to improve the mechanical behaviour of soils through compaction or cement grouting dates to the 60s. The increasing trends of urbanization worldwide require new solutions for the development of resilient and s ...
Data augmentation has proven its usefulness to improve model generalization and performance. While it is commonly applied in computer vision application when it comes to multi-view systems, it is rarely used. Indeed geometric data augmentation can break th ...
As an 'early alerting' sense, one of the primary tasks for the human visual system is to recognize distant objects. In the specific context of facial identification, this ecologically important task has received surprisingly little attention. Most studies ...
In the past years, deep convolutional neural networks have been pushing the frontier of face recognition (FR) techniques in both verification and identification scenarios. Despite the high accuracy, they are often criticized for lacking explainability. The ...
Current machine learning models for vision are often highly specialized and limited to a single modality and task. In contrast, recent large language models exhibit a wide range of capabilities, hinting at a possibility for similarly versatile models in co ...
Megapixel single-photon avalanche diode (SPAD) arrays have been developed recently, opening up the possibility of deploying SPADs as general-purpose passive cameras for photography and computer vision. However, most previous work on SPADs has been limited ...
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 ...
Despite the significant progress in recent years, deep face recognition is often treated as a "black box" and has been criticized for lacking explainability. It becomes increasingly important to understand the characteristics and decisions of deep face rec ...
