Accurate Disparity Estimation for Plenoptic Images

@inproceedings{Sabater2014AccurateDE,
  title={Accurate Disparity Estimation for Plenoptic Images},
  author={Neus Sabater and Mozhdeh Seifi and Valter Drazic and Gustavo Sandri and Patrick P{\'e}rez},
  booktitle={ECCV Workshops},
  year={2014}
}
In this paper we propose a post-processing pipeline to recover accurately the views (light-field) from the raw data of a plenoptic camera such as Lytro and to estimate disparity maps in a novel way from such a light-field. [...] Key Method First, the microlens centers are estimated and then the raw image is demultiplexed without demosaicking it beforehand. Then, we present a new block-matching algorithm to estimate disparities for the mosaicked plenoptic views.Expand
An Image Rendering Pipeline for Focused Plenoptic Cameras
TLDR
A new algorithm for microlens center calibration fully in the Fourier domain, a novel algorithm for depth map computation using a stereo focal stack, and a depth-based rendering algorithm that is able to refocus at a particular depth or to create all-in-focus images are proposed.
On plenoptic sub-aperture view recovery
TLDR
A fast framework to re-grid, denoise and up-sample the data of any plenoptic camera using the prior sub-pixel estimation of micro-images centers and of inter-views disparities is proposed.
Over- and Under-Exposure Reconstruction of a Single Plenoptic Capture
TLDR
This work presents a straightforward and robust plenoptic reconstruction technique based on the observation that vignetting causes peripheral views to receive less light than central views, and accurately reconstructs under- and over-exposed regions (known as declipping).
Super-resolution image synthesis using the physical pixel arrangementofalight field camera
TLDR
A method for super-resolution image synthesis that accurately handles the physical pixel arrangement of a light field (plenoptic) camera through a micro-lens array and can achieve higher image quality than that with a standard Light Field Toolbox is proposed.
Motion Deblurring for Plenoptic Images
TLDR
A highly parallelizable model for light field motion blur that is computationally and memory efficient and handles practical issues in real cameras such as radial distortion correction and alignment within an energy minimization framework is introduced.
Robust and Dense Depth Estimation for Light Field Images
TLDR
This work proposes a disparity interpolation method increasing the density and improving the accuracy of this initial estimate of disparity maps between specific pairs of views, and proposes a depth estimation method for light field images.
Reliable light field multiwindow disparity estimation
  • J. Navarro, A. Buades
  • Computer Science
    2016 IEEE International Conference on Image Processing (ICIP)
  • 2016
TLDR
This work proposes a depth estimation method for light field images by computing disparity maps between specific pairs of views and provides a mask of incorrect matches to obtain a unique and robust estimation.
A NOVEL DISPARITY-ASSISTED BLOCK MATCHING-BASED APPROACH FOR SUPER-RESOLUTION OF LIGHT FIELD IMAGES
  • S. Farag, V. Velisavljevic
  • Computer Science
    2018 - 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)
  • 2018
TLDR
A novel super-resolution technique is proposed with a focus on exploiting estimated disparity information to reduce the matching area in the super- resolution process, and it is proved a steady gain in the PSNR and SSIM quality of thesuper-resolved images for the resolution enhancement factor 8×8.
Disparity Estimation for Camera Arrays Using Reliability Guided Disparity Propagation
TLDR
This paper proposes a method to estimate the disparity from camera arrays by introducing a novel prior and inferring the corresponding implementation algorithm named reliability guided disparity propagation (RGDP).
Bilayer Blind Deconvolution with the Light Field Camera
In this paper we propose a solution to blind deconvolution of a scene with two layers (foreground/background). We show that the reconstruction of the support of these two layers from a single image
...
1
2
3
4
...

References

SHOWING 1-10 OF 27 REFERENCES
An analysis of color demosaicing in plenoptic cameras
TLDR
A simple but effective technique for improving the image resolution of the plenoptic camera by maneuvering the demosaicing process and can achieve visible resolution enhancement on dynamic refocusing and depth-assisted deep focus rendering.
Disparity-guided demosaicking of light field images
TLDR
This paper exploits the redundant sampling of scene content in the views, and shows that disparities estimated from the mosaicked data can guide the demosaicking, resulting in minimum artifacts compared to the state of art methods.
Full-Resolution Depth Map Estimation from an Aliased Plenoptic Light Field
TLDR
A novel algorithm which exploits a photoconsistency constraint specific to light fields captured with plenoptic cameras is proposed, combined with an efficient regularization scheme to give depth maps at a higher resolution than in any previous method.
Refocusing plenoptic images using depth-adaptive splatting
TLDR
A simple, novel plane sweep technique for refocusing plenoptic images, which antialiases out-of-focus regions, while keeping in- focus regions sharp.
The Light Field Camera: Extended Depth of Field, Aliasing, and Superresolution
  • Tom E. Bishop, P. Favaro
  • Computer Science, Medicine
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2012
TLDR
This work addresses traditional multiview stereo methods to the extracted low-resolution views can result in reconstruction errors due to aliasing, and incorporates Lambertian and texture preserving priors to reconstruct both scene depth and its superresolved texture in a variational Bayesian framework.
Modeling the Calibration Pipeline of the Lytro Camera for High Quality Light-Field Image Reconstruction
TLDR
This paper describes step-by-step procedures to calibrate a raw light-field image and proposes a learning based interpolation method which demonstrates a higher quality image reconstruction than previous interpolation methods including a method used in Lytro software.
Variational Light Field Analysis for Disparity Estimation and Super-Resolution
TLDR
The problem of view synthesis is formulated as a continuous inverse problem, which allows us to correctly take into account foreshortening effects caused by scene geometry transformations, and all optimization problems are solved with state-of-the-art convex relaxation techniques.
Quadratic formulation of disparity estimation problem for light-field camera
TLDR
This paper exploits the property of the views captured by the LF camera to formulate disparity estimation problem as a quadratic energy minimization problem and allows computation of continuous disparity with subpixel accuracy.
Superresolution with the focused plenoptic camera
TLDR
An approach for superresolving plenoptic images that takes place at the time of demosaicing the raw color image data is presented and the theoretical possibility for rendering final images at full sensor resolution is shown.
Depth from Combining Defocus and Correspondence Using Light-Field Cameras
TLDR
A novel simple and principled algorithm is presented that computes dense depth estimation by combining both defocus and correspondence depth cues, and shows how to combine the two cues into a high quality depth map, suitable for computer vision applications such as matting, full control of depth-of-field, and surface reconstruction.
...
1
2
3
...