Related papers: VLocNet++: Deep Multitask Learning for Semantic Vi…

Robust visual localization under a wide range of viewing conditions is a fundamental problem in computer vision. Handling the difficult cases of this problem is not only very challenging but also of high practical relevance, e.g., in the…

We develop new algorithms for simultaneous learning of multiple tasks (e.g., image classification, depth estimation), and for adapting to unseen task/domain distributions within those high-level tasks (e.g., different environments). First,…

Robust and accurate localization is critical for autonomous driving. Traditional GNSS-based localization methods suffer from signal occlusion and multipath effects in urban environments. Meanwhile, methods relying on high-definition (HD)…

For applications such as autonomous driving, self-localization/camera pose estimation and scene parsing are crucial technologies. In this paper, we propose a unified framework to tackle these two problems simultaneously. The uniqueness of…

Semantic segmentation of remote sensing images plays a vital role in a wide range of Earth Observation applications, such as land use land cover mapping, environment monitoring, and sustainable development. Driven by rapid developments in…

Visual odometry (VO) is a prevalent way to deal with the relative localization problem, which is becoming increasingly mature and accurate, but it tends to be fragile under challenging environments. Comparing with classical geometry-based…

Deep learning and convolutional neural networks (ConvNets) have been successfully applied to most relevant tasks in the computer vision community. However, these networks are computationally demanding and not suitable for embedded devices…

Accurate perception of dynamic traffic scenes is crucial for high-level autonomous driving systems, requiring robust object motion estimation and instance segmentation. However, traditional methods often treat them as separate tasks,…

Humans naturally perceive a 3D scene in front of them through accumulation of information obtained from multiple interconnected projections of the scene and by interpreting their correspondence. This phenomenon has inspired artificial…

The global rise in the number of people with physical disabilities, in part due to improvements in post-trauma survivorship and longevity, has amplified the demand for advanced assistive technologies to improve mobility and independence.…

We present a novel method to fuse the power of deep networks with the computational efficiency of geometric and probabilistic localization algorithms. In contrast to other methods that completely replace a classical visual estimator with a…

Extreme head postures pose a common challenge across a spectrum of facial analysis tasks, including face detection, facial landmark detection (FLD), and head pose estimation (HPE). These tasks are interdependent, where accurate FLD relies…

Scene understanding enables intelligent agents to interpret and comprehend their environment. While existing large vision-language models (LVLMs) for scene understanding have primarily focused on indoor household tasks, they face two…

This paper introduces self-supervised neural network models to tackle several fundamental problems in the field of 3D human body analysis and processing. First, we propose VariShaPE (Varifold Shape Parameter Estimator), a novel architecture…

Visual-Semantic Embedding (VSE) is a prevalent approach in image-text retrieval by learning a joint embedding space between the image and language modalities where semantic similarities would be preserved. The triplet loss with…

Visual place recognition (VPR) remains challenging due to significant viewpoint changes and appearance variations. Mainstream works tackle these challenges by developing various feature aggregation methods to transform deep features into…

Visual place recognition is one of the essential and challenging problems in the fields of robotics. In this letter, we for the first time explore the use of multi-modal fusion of semantic and visual modalities in dynamics-invariant space…

This dissertation addresses visual scene understanding and enhances segmentation performance and generalization, training efficiency of networks, and holistic understanding. First, we investigate semantic segmentation in the context of…

This study aims to improve the performance and generalization capability of end-to-end autonomous driving with scene understanding leveraging deep learning and multimodal sensor fusion techniques. The designed end-to-end deep neural network…

We study the task of embodied visual active learning, where an agent is set to explore a 3d environment with the goal to acquire visual scene understanding by actively selecting views for which to request annotation. While accurate on some…