Related papers: Learning Transformations To Reduce the Geometric S…

Unaligned Scene Change Detection aims to detect scene changes between image pairs captured at different times without assuming viewpoint alignment. To handle viewpoint variations, current methods rely solely on 2D visual cues to establish…

Convolutional Neural networks (CNN) have been the first choice of paradigm in many computer vision applications. The convolution operation however has a significant weakness which is it only operates on a local neighborhood of pixels, thus…

We present a low-rank transformation approach to compensate for face variations due to changes in visual domains, such as pose and illumination. The key idea is to learn discriminative linear transformations for face images using matrix…

Domain generalisation aims to promote the learning of domain-invariant features while suppressing domain-specific features, so that a model can generalise better to previously unseen target domains. An approach to domain generalisation for…

A significant challenge in the field of object detection lies in the system's performance under non-ideal imaging conditions, such as rain, fog, low illumination, or raw Bayer images that lack ISP processing. Our study introduces "Feature…

Deep learning has shown to be effective for robust and real-time monocular image relocalisation. In particular, PoseNet is a deep convolutional neural network which learns to regress the 6-DOF camera pose from a single image. It learns to…

Recent deep learning methods for object detection rely on a large amount of bounding box annotations. Collecting these annotations is laborious and costly, yet supervised models do not generalize well when testing on images from a different…

Digital twins are meant to bridge the gap between real-world physical systems and virtual representations. Both stand-alone and descriptive digital twins incorporate 3D geometric models, which are the physical representations of objects in…

We present a novel approach to background subtraction that is based on the local shape of small image regions. In our approach, an image region centered on a pixel is mod-eled using the local self-similarity descriptor. We aim at obtaining…

Visual Transformers (VTs) are emerging as an architectural paradigm alternative to Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations between image elements and they potentially have a larger…

In the domain of autonomous driving, deep learning has substantially improved the 3D object detection accuracy for LiDAR and stereo camera data alike. While deep networks are great at generalization, they are also notorious to over-fit to…

Despite growing interest in object detection, very few works address the extremely practical problem of cross-domain robustness especially for automative applications. In order to prevent drops in performance due to domain shift, we…

Many machine learning methods operate by inverting a neural network at inference time, which has become a popular technique for solving inverse problems in computer vision, robotics, and graphics. However, these methods often involve…

Most object detection methods for autonomous driving usually assume a consistent feature distribution between training and testing data, which is not always the case when weathers differ significantly. The object detection model trained…

This paper addresses the problem of fast learning of radar detectors with a limited amount of training data. In current data-driven approaches for radar detection, re-training is generally required when the operating environment changes,…

Spatial perception aims to estimate camera motion and scene structure from visual observations, a problem traditionally addressed through geometric modeling and physical consistency constraints. Recent learning-based methods have…

Leveraging synthetically rendered data offers great potential to improve monocular depth estimation and other geometric estimation tasks, but closing the synthetic-real domain gap is a non-trivial and important task. While much recent work…

Adjusting camera exposure in arbitrary lighting conditions is the first step to ensure the functionality of computer vision applications. Poorly adjusted camera exposure often leads to critical failure and performance degradation.…

Training networks to perform metric relocalization traditionally requires accurate image correspondences. In practice, these are obtained by restricting domain coverage, employing additional sensors, or capturing large multi-view datasets.…

A commercial robot, trained by its manufacturer to recognize a predefined number and type of objects, might be used in many settings, that will in general differ in their illumination conditions, background, type and degree of clutter, and…