English
Related papers

Related papers: Multi-Task Learning of Height and Semantics from A…

200 papers

The visual entities in cross-view images exhibit drastic domain changes due to the difference in viewpoints each set of images is captured from. Existing state-of-the-art methods address the problem by learning view-invariant descriptors…

Computer Vision and Pattern Recognition · Computer Science 2019-08-12 Krishna Regmi , Mubarak Shah

Elevation maps are commonly used to represent the environment of mobile robots and are instrumental for locomotion and navigation tasks. However, pure geometric information is insufficient for many field applications that require appearance…

Robotics · Computer Science 2024-10-28 Gian Erni , Jonas Frey , Takahiro Miki , Matias Mattamala , Marco Hutter

Multi-modal large language models (MLLMs) have rapidly advanced in visual tasks, yet their spatial understanding remains limited to single images, leaving them ill-suited for physical-world applications that require multi-frame reasoning.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Runsen Xu , Weiyao Wang , Hao Tang , Xingyu Chen , Xiaodong Wang , Fu-Jen Chu , Matt Feiszli , Kevin J. Liang

Multi-task learning (MTL) improves prediction performance in different contexts by learning models jointly on multiple different, but related tasks. Network data, which are a priori data with a rich relational structure, provide an…

Machine Learning · Statistics 2014-11-11 Chen Fang , Daniel N. Rockmore

This paper considers outdoor terrain mapping using RGB images obtained from an aerial vehicle. While feature-based localization and mapping techniques deliver real-time vehicle odometry and sparse keypoint depth reconstruction, a dense…

Computer Vision and Pattern Recognition · Computer Science 2024-01-18 Qiaojun Feng , Nikolay Atanasov

This paper studies image-based geo-localization (IBL) problem using ground-to-aerial cross-view matching. The goal is to predict the spatial location of a ground-level query image by matching it to a large geotagged aerial image database…

Computer Vision and Pattern Recognition · Computer Science 2019-04-01 Liu Liu , Hongdong Li

We present a novel multi-view training framework and CNN architecture for combining information from multiple overlapping satellite images and noisy training labels derived from OpenStreetMap (OSM) to semantically label buildings and roads…

Computer Vision and Pattern Recognition · Computer Science 2024-10-30 Bharath Comandur , Avinash C. Kak

Understanding the geometric and semantic properties of the scene is crucial in autonomous navigation and particularly challenging in the case of Unmanned Aerial Vehicle (UAV) navigation. Such information may be by obtained by estimating…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Yara AlaaEldin , Francesca Odone

Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manner. However, very few explore geometric properties revealing…

Computer Vision and Pattern Recognition · Computer Science 2020-09-18 Lulu Tang , Ke Chen , Chaozheng Wu , Yu Hong , Kui Jia , Zhixin Yang

A common approach for modeling the environment of an autonomous vehicle are dynamic occupancy grid maps, in which the surrounding is divided into cells, each containing the occupancy and velocity state of its location. Despite the advantage…

Robotics · Computer Science 2022-05-06 Marcel Schreiber , Vasileios Belagiannis , Claudius Gläser , Klaus Dietmayer

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,…

Machine Learning · Computer Science 2020-06-16 Kiran Lekkala , Laurent Itti

It is still challenging to build an AI system that can perform tasks that involve vision and language at human level. So far, researchers have singled out individual tasks separately, for each of which they have designed networks and…

Computer Vision and Pattern Recognition · Computer Science 2018-12-04 Duy-Kien Nguyen , Takayuki Okatani

Aerial images play a vital role in urban planning and environmental preservation, as they consist of various structures, representing different types of buildings, forests, mountains, and unoccupied lands. Due to its heterogeneous nature,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Subhajeet Das , Susmita Ghosh , Abhiroop Chatterjee

This paper presents an analysis of utilizing elevation data to aid outdoor point cloud semantic segmentation through existing machine-learning networks in remote sensing, specifically in urban, built-up areas. In dense outdoor point clouds,…

Computer Vision and Pattern Recognition · Computer Science 2025-01-31 Kevin Qiu , Dimitri Bulatov , Dorota Iwaszczuk

High-resolution aerial images have a wide range of applications, such as military exploration, and urban planning. Semantic segmentation is a fundamental method extensively used in the analysis of high-resolution aerial images. However, the…

Computer Vision and Pattern Recognition · Computer Science 2019-07-09 Jingbo Lin , Weipeng Jing , Houbing Song

Neural Radiance Fields (NeRF) offer the potential to benefit 3D reconstruction tasks, including aerial photogrammetry. However, the scalability and accuracy of the inferred geometry are not well-documented for large-scale aerial…

Computer Vision and Pattern Recognition · Computer Science 2024-06-07 Ningli Xu , Rongjun Qin , Debao Huang , Fabio Remondino

We present a neural radiance field method for urban-scale semantic and building-level instance segmentation from aerial images by lifting noisy 2D labels to 3D. This is a challenging problem due to two primary reasons. Firstly, objects in…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Yuqi Zhang , Guanying Chen , Jiaxing Chen , Shuguang Cui

This paper addresses the problem of geometric scene parsing, i.e. simultaneously labeling geometric surfaces (e.g. sky, ground and vertical plane) and determining the interaction relations (e.g. layering, supporting, siding and affinity)…

Computer Vision and Pattern Recognition · Computer Science 2016-04-11 Zhanglin Peng , Ruimao Zhang , Xiaodan Liang , Xiaobai Liu , Liang Lin

Image retrieval refers to finding relevant images from an image database for a query, which is considered difficult for the gap between low-level representation of images and high-level representation of queries. Recently further developed…

Computer Vision and Pattern Recognition · Computer Science 2013-12-24 Yalong Bai , Kuiyuan Yang , Wei Yu , Wei-Ying Ma , Tiejun Zhao

In this work, we propose a cross-view learning approach, in which images captured from a ground-level view are used as weakly supervised annotations for interpreting overhead imagery. The outcome is a convolutional neural network for…

Computer Vision and Pattern Recognition · Computer Science 2018-08-06 Connor Greenwell , Scott Workman , Nathan Jacobs