scholarly journals Learning Light Field Angular Super-Resolution via a Geometry-Aware Network

2020 ◽  
Vol 34 (07) ◽  
pp. 11141-11148 ◽  
Author(s):  
Jing Jin ◽  
Junhui Hou ◽  
Hui Yuan ◽  
Sam Kwong
Keyword(s):  
Light Field ◽  
Angular Resolution ◽  
State Of The Art ◽  
Super Resolution ◽  
Depth Estimation ◽  
High Angular Resolution ◽  
Intrinsic Geometry ◽  
Physically Based ◽  
Small Baseline ◽  
Significant Superiority

The acquisition of light field images with high angular resolution is costly. Although many methods have been proposed to improve the angular resolution of a sparsely-sampled light field, they always focus on the light field with a small baseline, which is captured by a consumer light field camera. By making full use of the intrinsic geometry information of light fields, in this paper we propose an end-to-end learning-based approach aiming at angularly super-resolving a sparsely-sampled light field with a large baseline. Our model consists of two learnable modules and a physically-based module. Specifically, it includes a depth estimation module for explicitly modeling the scene geometry, a physically-based warping for novel views synthesis, and a light field blending module specifically designed for light field reconstruction. Moreover, we introduce a novel loss function to promote the preservation of the light field parallax structure. Experimental results over various light field datasets including large baseline light field images demonstrate the significant superiority of our method when compared with state-of-the-art ones, i.e., our method improves the PSNR of the second best method up to 2 dB in average, while saves the execution time 48×. In addition, our method preserves the light field parallax structure better.

scholarly journals Fast and Accurate Light Field View Synthesis by Optimizing Input View Selection

Micromachines ◽  
2021 ◽  
Vol 12 (5) ◽  
pp. 557
Author(s):  
Xingzheng Wang ◽  
Yongqiang Zan ◽  
Senlin You ◽  
Yuanlong Deng ◽  
Lihua Li
Keyword(s):  
Spatial Resolution ◽  
Light Field ◽  
Angular Resolution ◽  
Super Resolution ◽  
Depth Estimation ◽  
View Synthesis ◽  
The Novel ◽  
Arbitrary Location ◽  
Field View

There is a trade-off between spatial resolution and angular resolution limits in light field applications; various targeted algorithms have been proposed to enhance angular resolution while ensuring high spatial resolution simultaneously, which is also called view synthesis. Among them, depth estimation-based methods can use only four corner views to reconstruct a novel view at an arbitrary location. However, depth estimation is a time-consuming process, and the quality of the reconstructed novel view is not only related to the number of the input views, but also the location of the input views. In this paper, we explore the relationship between different input view selections with the angular super-resolution reconstruction results. Different numbers and positions of input views are selected to compare the speed of super-resolution reconstruction and the quality of novel views. Experimental results show that the speed of the algorithm decreases with the increase of the input views for each novel view, and the quality of the novel view decreases with the increase of the distance from the input views. After comparison using two input views in the same line to reconstruct the novel views between them, fast and accurate light field view synthesis is achieved.

scholarly journals Attention-Based View Selection Networks for Light-Field Disparity Estimation

2020 ◽  
Vol 34 (07) ◽  
pp. 12095-12103
Author(s):  
Yu-Ju Tsai ◽  
Yu-Lun Liu ◽  
Ming Ouhyoung ◽  
Yung-Yu Chuang
Keyword(s):  
Light Field ◽  
State Of The Art ◽  
Depth Estimation ◽  
Disparity Estimation ◽  
View Selection ◽  
Deep Network ◽  
Depth Maps ◽  
Improve Accuracy ◽  
Light Field Image ◽  
Symmetric Property

This paper introduces a novel deep network for estimating depth maps from a light field image. For utilizing the views more effectively and reducing redundancy within views, we propose a view selection module that generates an attention map indicating the importance of each view and its potential for contributing to accurate depth estimation. By exploring the symmetric property of light field views, we enforce symmetry in the attention map and further improve accuracy. With the attention map, our architecture utilizes all views more effectively and efficiently. Experiments show that the proposed method achieves state-of-the-art performance in terms of accuracy and ranks the first on a popular benchmark for disparity estimation for light field images.

scholarly journals FOD-Net: A Deep Learning Method for Fiber Orientation Distribution Angular Super Resolution

2021 ◽  
Author(s):  
Rui Zeng ◽  
Jinglei Lv ◽  
He Wang ◽  
Luping Zhou ◽  
Michael Barnett ◽  
...  
Keyword(s):  
Deep Learning ◽  
Angular Resolution ◽  
Super Resolution ◽  
Orientation Distribution ◽  
Quality Data ◽  
High Angular Resolution ◽  
Clinical Protocols ◽  
High Quality ◽  
Human Connectome Project ◽  
Fiber Orientation Distribution

ABSTRACTMapping the human connectome using fibre-tracking permits the study of brain connectivity and yields new insights into neuroscience. However, reliable connectome reconstruction using diffusion magnetic resonance imaging (dMRI) data acquired by widely available clinical protocols remains challenging, thus limiting the connectome/tractography clinical applications. Here we develop fibre orientation distribution (FOD) network (FOD-Net), a deep-learning-based framework for FOD angular super-resolution. Our method enhances the angular resolution of FOD images computed from common clinical-quality dMRI data, to obtain FODs with quality comparable to those produced from advanced research scanners. Super-resolved FOD images enable superior tractography and structural connectome reconstruction from clinical protocols. The method was trained and tested with high-quality data from the Human Connectome Project (HCP) and further validated with a local clinical 3.0T scanner. Using this method, we improve the angular resolution of FOD images acquired with typical single-shell low-angular-resolution dMRI data (e.g., 32 directions, b=1000 s/mm2) to approximate the quality of FODs derived from time-consuming, multi-shell high-angular-resolution dMRI research protocols. We also demonstrate tractography improvement, removing spurious connections and bridging missing connections. We further demonstrate that connectomes reconstructed by super-resolved FOD achieve comparable results to those obtained with more advanced dMRI acquisition protocols, on both HCP and clinical 3T data. Advances in deep-learning approaches used in FOD-Net facilitate the generation of high quality tractography/connectome analysis from existing clinical MRI environments.

A High-angular-resolution Turntable Data-set for Experiments on Light Field Visualization Quality

2018 ◽  
Author(s):  
Roopak R. Tamboli ◽  
M. Shanmukh Reddy ◽  
Peter A. Kara ◽  
Maria G. Martini ◽  
Sumohana S. Channappayya ◽  
...  
Keyword(s):  
Light Field ◽  
Angular Resolution ◽  
High Angular Resolution ◽  
Data Set

Improved Depth Estimation for Occlusion Scenes Using a Light-Field Camera

2020 ◽  
Vol 86 (7) ◽  
pp. 443-456
Author(s):  
Changkun Yang ◽  
Zhaoqin Liu ◽  
Kaichang Di ◽  
Changqing Hu ◽  
Yexin Wang ◽  
...  
Keyword(s):  
Field Data ◽  
Light Field ◽  
State Of The Art ◽  
Depth Estimation ◽  
Data Sets ◽  
Identification Algorithm ◽  
Novel Method ◽  
Light Field Imaging ◽  
The Cost ◽  
Field Imaging

With the development of light-field imaging technology, depth estimation using light-field cameras has become a hot topic in recent years. Even through many algorithms have achieved good performance for depth estimation using light-field cameras, removing the influence of occlusion, especially multi-occlusion, is still a challenging task. The photo-consistency assumption does not hold in the presence of occlusions, which makes most depth estimation of light-field imaging unreliable. In this article, a novel method to handle complex occlusion in depth estimation of light-field imaging is proposed. The method can effectively identify occluded pixels using a refocusing algorithm, accurately select unoccluded views using the adaptive unoccluded-view identification algorithm, and then improve the depth estimation by computing the cost volumes in the unoccluded views. Experimental results demonstrate the advantages of our proposed algorithm compared with conventional state-of-the art algorithms on both synthetic and real light-field data sets.

scholarly journals GALACTICNUCLEUS: A high-angular-resolution JHKs imaging survey of the Galactic centre

2019 ◽  
Vol 631 ◽  
pp. A20 ◽  
Author(s):  
F. Nogueras-Lara ◽  
R. Schödel ◽  
A. T. Gallego-Calvente ◽  
H. Dong ◽  
E. Gallego-Cano ◽  
...  
Keyword(s):  
Stellar Population ◽  
Near Infrared ◽  
Milky Way ◽  
Angular Resolution ◽  
State Of The Art ◽  
Zero Point ◽  
Uncertainty Estimation ◽  
Galactic Centre ◽  
High Angular Resolution ◽  
Central Regions

Context. The high extinction and extreme source crowding of the central regions of the Milky Way are serious obstacles to the study of the structure and stellar population of the Galactic centre (GC). Existing surveys that cover the GC region (2MASS, UKIDSS, VVV, SIRIUS) do not have the necessary high angular resolution. Therefore, a high-angular-resolution survey in the near infrared is crucial to improve the state of the art. Aims. Here, we present the GALACTICNUCLEUS catalogue, a near infrared JHKs high-angular-resolution (0.2″) survey of the nuclear bulge of the Milky Way. Methods. We explain in detail the data reduction, data analysis, calibration, and uncertainty estimation of the GALACTICNUCLEUS survey. We assess the data quality comparing our results with previous surveys. Results. We obtained accurate JHKs photometry for ∼3.3 × 106 stars in the GC detecting around 20% in J, 65% in H, and 90% in Ks. The survey covers a total area of ∼0.3 deg2, which corresponds to ∼6000 pc2. The GALACTICNUCLEUS survey reaches 5σ detections for J ∼ 22 mag, H ∼ 21 mag, and Ks ∼ 21 mag. The uncertainties are below 0.05 mag at J ∼ 21 mag, H ∼ 19 mag, and Ks ∼ 18 mag. The zero point systematic uncertainty is ≲0.04 mag in all three bands. We present colour–magnitude diagrams for the different regions covered by the survey.

scholarly journals 16 m Large Slit Aperture Telescope for Very High Angular Resolution Astronomy

1984 ◽  
Vol 79 ◽  
pp. 295-308
Author(s):  
R.G. Petrov ◽  
C. Aime ◽  
J. Borgnino ◽  
F. Martin ◽  
G. Ricort
Keyword(s):  
Angular Resolution ◽  
Optical Axis ◽  
Super Resolution ◽  
Speckle Interferometry ◽  
High Angular Resolution ◽  
Imaging Methods ◽  
Full Coverage ◽  
Mechanical Constraints ◽  
The Cost ◽  
Very High

AbstractThe expected progress of diffraction limited imaging methods and the apparition of new super resolution techniques like differential speckle interferometry would justify the construction of a 15 m class telescope dedicated to diffraction limited observations in order to fulfil the potential of high angular resolution astrophysics of 15 m class instruments, but the construction of such a telescope is conceivable only if its cost is much smaller than the cost of the equivalent all purposes VLT. In this paper we suggest that a telescope with a long and thin rectangular primary ( 16 m X.4m say ) , able to rotate around the optical axis to ensure a full coverage of the frequency plane, would do almost as well than a conventional 16 m aperture telescope for high angular resolution astronomy for a cost substancially reduced. The performances of such a Large Slit Aperture Telescope ( LSAT ) for classical and differential speckle interferometry are examined and the releases on the optical and mechanical constraints allowed by the dedication of the instrument to speckle techniques are discussed.

Sign in / Sign up

Export Citation Format

Share Document