[HTML][HTML] A survey of state-of-the-art on visual SLAM

IA Kazerouni, L Fitzgerald, G Dooly, D Toal - Expert Systems with …, 2022 - Elsevier
This paper is an overview to Visual Simultaneous Localization and Mapping (V-SLAM). We
discuss the basic definitions in the SLAM and vision system fields and provide a review of …

Deep learning sensor fusion for autonomous vehicle perception and localization: A review

J Fayyad, MA Jaradat, D Gruyer, H Najjaran - Sensors, 2020 - mdpi.com
Autonomous vehicles (AV) are expected to improve, reshape, and revolutionize the future of
ground transportation. It is anticipated that ordinary vehicles will one day be replaced with …

Sparf: Neural radiance fields from sparse and noisy poses

P Truong, MJ Rakotosaona… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Neural Radiance Field (NeRF) has recently emerged as a powerful representation
to synthesize photorealistic novel views. While showing impressive performance, it relies on …

Understanding the limitations of cnn-based absolute camera pose regression

T Sattler, Q Zhou, M Pollefeys… - Proceedings of the …, 2019 - openaccess.thecvf.com
Visual localization is the task of accurate camera pose estimation in a known scene. It is a
key problem in computer vision and robotics, with applications including self-driving cars …

Relpose: Predicting probabilistic relative rotation for single objects in the wild

JY Zhang, D Ramanan, S Tulsiani - European Conference on Computer …, 2022 - Springer
We describe a data-driven method for inferring the camera viewpoints given multiple images
of an arbitrary object. This task is a core component of classic geometric pipelines such as …

Geometric loss functions for camera pose regression with deep learning

A Kendall, R Cipolla - … of the IEEE conference on computer …, 2017 - openaccess.thecvf.com
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 …

Visual SLAM and structure from motion in dynamic environments: A survey

MRU Saputra, A Markham, N Trigoni - ACM Computing Surveys (CSUR), 2018 - dl.acm.org
In the last few decades, Structure from Motion (SfM) and visual Simultaneous Localization
and Mapping (visual SLAM) techniques have gained significant interest from both the …

Viewformer: Nerf-free neural rendering from few images using transformers

J Kulhánek, E Derner, T Sattler, R Babuška - European Conference on …, 2022 - Springer
Novel view synthesis is a long-standing problem. In this work, we consider a variant of the
problem where we are given only a few context views sparsely covering a scene or an …

Deep auxiliary learning for visual localization and odometry

A Valada, N Radwan, W Burgard - 2018 IEEE international …, 2018 - ieeexplore.ieee.org
Localization is an indispensable component of a robot's autonomy stack that enables it to
determine where it is in the environment, essentially making it a precursor for any action …

Vlocnet++: Deep multitask learning for semantic visual localization and odometry

N Radwan, A Valada, W Burgard - IEEE Robotics and …, 2018 - ieeexplore.ieee.org
Semantic understanding and localization are fundamental enablers of robot autonomy that
have been tackled as disjoint problems for the most part. While deep learning has enabled …