Corpus ID: 221516790

Deep Sparse Light Field Refocusing

  title={Deep Sparse Light Field Refocusing},
  author={Shachar Ben Dayan and David Mendlovic and Raja Giryes},
Light field photography enables to record 4D images, containing angular information alongside spatial information of the scene. One of the important applications of light field imaging is post-capture refocusing. Current methods require for this purpose a dense field of angle views; those can be acquired with a micro-lens system or with a compressive system. Both techniques have major drawbacks to consider, including bulky structures and angular-spatial resolution trade-off. We present a novel… Expand

Figures and Tables from this paper

A Spatio-Angular Filter for High Quality Sparse Light Field Refocusing
  • Martin Alain, A. Smolic
  • Computer Science
  • 2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
  • 2021
A filter for removing angular aliasing artefacts in light field refocusing is proposed, which consists in modifying the well known shift-andsum algorithm to apply a depth-dependent blur to the light field in between the shift and the sum operations. Expand
Learning Coded Apertures for Time-Division Multiplexing Light Field Display
Conventional stereoscopic displays suffer from vergence-accommodation conflict which cause visual fatigue. Integral imaging-based (II) displays resolves this problem by directly projecting lightExpand


Fast and accurate reconstruction of compressed color light field
This work proposes a computationally efficient neural network that recovers a high-quality color light field from a single coded image, and proposes a neural network for depth map extraction based on the decompressed light field, which is trained in an unsupervised manner without the ground truth depth map. Expand
Compressive Light Field Reconstructions Using Deep Learning
A deep learning approach using a new, two branch network architecture, consisting jointly of an autoencoder and a 4D CNN, to recover a high resolution 4D light field from a single coded 2D image, decreases reconstruction time significantly while achieving average PSNR values of 26-32 dB on a variety of light fields. Expand
Compressive light field photography using overcomplete dictionaries and optimized projections
A compressive light field camera architecture that allows for higher-resolution light fields to be recovered than previously possible from a single image, and a variety of other applications for light field atoms and sparse coding, including 4D light field compression and denoising are demonstrated. Expand
Light Field Reconstruction Using Deep Convolutional Network on EPI
In this paper, we take advantage of the clear texture structure of the epipolar plane image (EPI) in the light field data and model the problem of light field reconstruction from a sparse set ofExpand
Learning-based view synthesis for light field cameras
This paper proposes a novel learning-based approach to synthesize new views from a sparse set of input views that could potentially decrease the required angular resolution of consumer light field cameras, which allows their spatial resolution to increase. Expand
Depth from a Light Field Image with Learning-Based Matching Costs
A pipeline that automatically determines the best configuration for photo-consistency measure, which leads to the most reliable depth label from the light field, which was competitive with several state-of-the-art methods for the benchmark and real-world light field datasets. Expand
Light field denoising, light field superresolution and stereo camera based refocussing using a GMM light field patch prior
  • K. Mitra, A. Veeraraghavan
  • Mathematics, Computer Science
  • 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
  • 2012
This work proposes a patch based approach, where it is shown that the light field patches with the same disparity value lie on a low-dimensional subspace and that the dimensionality of such subspaces varies quadratically with the disparity value. Expand
Synthesizing a 4D Spatio-Angular Consistent Light Field from a Single Image
A single end-to-end deep neural network that does not require a physical-based approach nor a post-processing subnetwork is proposed and successfully synthesizes dense light fields and qualitatively and quantitatively outperforms the previous model. Expand
End-to-End View Synthesis for Light Field Imaging with Pseudo 4DCNN
An end-to-end deep learning framework to solve limited angular resolution problems by exploring Pseudo 4DCNN and shows good performances in real-world applications such as biometrics and depth estimation. Expand
Programmable aperture photography: multiplexed light field acquisition
A system including a novel component called programmable aperture and two associated post-processing algorithms for high-quality light field acquisition and the effectiveness of the system and the quality of the captured light field is presented. Expand