paper-with-me

Papers

Graph-Based Classification of Omnidirectional Images

2017-07-26 · Renata Khasanova, Pascal Frossard

Omnidirectional cameras are widely used in such areas as robotics and virtual reality as they provide a wide field of view. Their images are often processed with classical methods, which might unfortunately lead to non-optimal solutions as these methods are designed for planar images that have different geometrical properties than omnidirectional ones. In this paper we study image classification task by taking into account the specific geometry of omnidirectional cameras with graph-based representations. In particular, we extend deep learning architectures to data on graphs; we propose a principled way of graph construction such that convolutional filters respond similarly for the same pattern on different positions of the image regardless of lens distortions. Our experiments show that the proposed method outperforms current techniques for the omnidirectional image classification problem.

📄 PDF Abstract BibTeX arXiv:1707.08301

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral Classificationgraph constructionimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Distortion-Adaptive Grape Bunch Counting for Omnidirectional Images

2020-08-28 · Ryota Akai, Yuzuko Utsumi, Yuka Miwa, Masakazu Iwamura 외

This paper proposes the first object counting method for omnidirectional images. Because conventional object counting methods cannot handle the distortion of omnidirectional images, we propose to process them using stere…

Data AugmentationObject Counting

Blind Omnidirectional Image Quality Assessment with Viewport Oriented Graph Convolutional Networks

2020-08-21

Quality assessment of omnidirectional images has become increasingly urgent due to the rapid growth of virtual reality applications. Different from traditional 2D images and videos, omnidirectional contents can provide c…

Image Quality Assessment

Geometry aware convolutional filters for omnidirectional images representation

2019-05-01 · ICLR 2019 5 · Renata Khasanova, Pascal Frossard

Due to their wide field of view, omnidirectional cameras are frequently used by autonomous vehicles, drones and robots for navigation and other computer vision tasks. The images captured by such cameras, are often analys…

Autonomous Vehiclesimage-classificationImage Classification

OSLO: On-the-Sphere Learning for Omnidirectional images and its application to 360-degree image compression

2021-07-19 · Navid Mahmoudian Bidgoli, Roberto G. de A. Azevedo, Thomas Maugey, Aline Roumy 외

State-of-the-art 2D image compression schemes rely on the power of convolutional neural networks (CNNs). Although CNNs offer promising perspectives for 2D image compression, extending such models to omnidirectional image…

Image Compression

TomoGraphView: 3D Medical Image Classification with Omnidirectional Slice Representations and Graph Neural Networks

2025-11-12 · Johannes Kiechle, Stefan M. Fischer, Daniel M. Lang, Cosmin I. Bercea 외 arxiv

The sharp rise in medical tomography examinations has created a demand for automated systems that can reliably extract informative features for downstream tasks such as tumor characterization. Although 3D volumes contain…

Medical Image Classification3D Classification