Low illumination underwater light field images reconstruction using deep convolutional neural networks

H Lu, Y Li, T Uemura, H Kim, S Serikawa - Future Generation Computer …, 2018 - Elsevier
Underwater optical images are usually influenced by low lighting, high turbidity scattering
and wavelength absorption. To solve these issues, a great deal of work has been performed …

3d scene geometry estimation from 360 imagery: A survey

TLT da Silveira, PGL Pinto… - ACM Computing …, 2022 - dl.acm.org
This article provides a comprehensive survey on pioneer and state-of-the-art 3D scene
geometry estimation methodologies based on single, two, or multiple images captured …

Geometric calibration of micro-lens-based light field cameras using line features

Y Bok, HG Jeon, IS Kweon - IEEE transactions on pattern …, 2016 - ieeexplore.ieee.org
We present a novel method for the geometric calibration of micro-lens-based light field
cameras. Accurate geometric calibration is the basis of various applications. Instead of using …

Unstructured light fields

A Davis, M Levoy, F Durand - Computer Graphics Forum, 2012 - Wiley Online Library
We present a system for interactively acquiring and rendering light fields using a hand‐held
commodity camera. The main challenge we address is assisting a user in achieving good …

Line assisted light field triangulation and stereo matching

Z Yu, X Guo, H Lin, A Lumsdaine… - Proceedings of the IEEE …, 2013 - openaccess.thecvf.com
Light fields are image-based representations that use densely sampled rays as a scene
description. In this paper, we explore geometric structures of 3D lines in ray space for …

Ray image modeling for fast catadioptric light field rendering

Y Ding, J **ao - US Patent 8,432,435, 2013 - Google Patents
2. Description of Related Art Computer generated three dimensional, ie 3D, images are
desirable in various applications, such as research and enter tainment. There are various …

Orca: Glossy objects as radiance-field cameras

K Tiwary, A Dave, N Behari… - Proceedings of the …, 2023 - openaccess.thecvf.com
Reflections on glossy objects contain valuable and hidden information about the
surrounding environment. By converting these objects into cameras, we can unlock exciting …

Computational plenoptic imaging

G Wetzstein, I Ihrke, D Lanman… - Computer Graphics …, 2011 - Wiley Online Library
The plenoptic function is a ray‐based model for light that includes the colour spectrum as
well as spatial, temporal and directional variation. Although digital light sensors have greatly …

[PDF][PDF] Plenoptic signal processing for robust vision in field robotics

DG Dansereau - 2014 - core.ac.uk
This thesis proposes the use of plenoptic cameras for improving the robustness and
simplicity of machine vision in field robotics applications. Dust, rain, fog, snow, murky water …

Beyond Alhazen's problem: Analytical projection model for non-central catadioptric cameras with quadric mirrors

A Agrawal, Y Taguchi, S Ramalingam - CVPR 2011, 2011 - ieeexplore.ieee.org
Catadioptric cameras are widely used to increase the field of view using mirrors. Central
catadioptric systems having an effective single viewpoint are easy to model and use, but …