A Wide-Field-of-View Monocentric Light Field Camera

Dansereau, Donald G.; Schuster, Glenn M.; Ford, Joseph E.; Wetzstein, Gordon

doi:10.1109/cvpr.2017.400

Cited by 32 publications

(14 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Capturing high resolution light field and light field videos requires an excessively large amount of bandwidth, which has been the main barrier for light field imaging. Light fields and light field videos have varieties of applications such as refocusing [21], interactive 3D video [223], free-viewpoint television (FTV) [224], light field display [225], auto-stereoscopic 3D display [226], depth estimation and occlusion modeling [227,228,229], scene flow estimation [230], light field segmentation [231], stitching [232], material recognition [233], compositing light field video [217], and photo-real digital actors [234].…”

Section: Light Field Acquisition Techniquesmentioning

confidence: 99%

Computational Photography : High Dynamic Rangeand Light Fields

Hajisharif

2020

Linköping Studies in Science and Technology. Dissertations

View full text Add to dashboard Cite

show abstract

Section: Light Field Acquisition Techniquesmentioning

confidence: 99%

Computational Photography : High Dynamic Rangeand Light Fields

Hajisharif

2020

Linköping Studies in Science and Technology. Dissertations

View full text Add to dashboard Cite

show abstract

“…Rotating the external iris prevents additional vignetting and maintains a constant pupil across the image, emulating the angle-independent total internal reflection virtual aperture possible with monocentric lenses [5]. The system captured both indoor (Figure 3) and outdoor panoramas through sequential exposures and demonstrated post-capture spherical defocus correction of the curved image plane, refocusing, depth estimation, and resolution enhancement, the processing side of which is detailed in [6]. Correcting the nearly 390 µm defocus at the diagonal extremes of the image sensor proves the concept of merging a monocentric wide FOV lens with LF computation.…”

Section: Optical Relay and Sequential Testbed Systemmentioning

confidence: 99%

Panoramic Monocentric Light Field Camera

Schuster

Agurok

Ford

et al. 2017

Optical Design and Fabrication 2017 (Freeform, IODC, OFT)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The emergence of light field cameras [1] has enabled photographers to refocus an image after it is taken, which is an appealing feature and has led to new artistic creations. Light field imaging also has found a variety of applications, such as microscopy [2], materials recognition [3], vision-based robotic control [4], and autonomous navigation [5]. The light field being acquired is often a set of sub-aperture images from different perspectives in a single shot [6], although there are also alternatives to build up the light field from a stack of images [7], [8].…”

Section: Introductionmentioning

confidence: 99%

Computational Light Field Generation Using Deep Nonparametric Bayesian Learning

Meng

Sun

et al. 2019

IEEE Access

View full text Add to dashboard Cite

In this paper, we present a deep nonparametric Bayesian method to synthesize a light field from a single image. Conventionally, light-field capture requires special optical architecture, and the gain in angular resolution often comes at the expense of a reduction in spatial resolution. Techniques for computationally generating the light field from a single image can be expanded further to a variety of applications, ranging from microscopy and materials analysis to vision-based robotic control and autonomous vehicles. We treat the light field as multiple sub-aperture views, and to compute the novel viewpoints, our model contains three major components. First, a convolutional neural network is used for predicting the depth probability map from the image. Second, a multi-scale feature dictionary is constructed within a multi-layer dictionary learning network. Third, the novel views are synthesized taking into account both the probabilistic depth map and the multi-scale feature dictionary. The experiments show that our method outperforms several state-of-the-art novel view synthesis methods in delivering good image resolution. INDEX TERMS Image reconstruction, convolutional neural network, deep learning, nonparametric Bayesian, light field imaging.

show abstract

A Wide-Field-of-View Monocentric Light Field Camera

Cited by 32 publications

References 29 publications

Computational Photography : High Dynamic Rangeand Light Fields

Computational Photography : High Dynamic Rangeand Light Fields

Panoramic Monocentric Light Field Camera

Computational Light Field Generation Using Deep Nonparametric Bayesian Learning

Contact Info

Product

Resources

About