Light field completion using focal stack propagation

Broad, Terence; Grierson, Mick

doi:10.1145/2945078.2945132

Cited by 10 publications

(6 citation statements)

References 4 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Concerning the propagation of one inpainted view (by an arbitrary method) to the rest of the light field, very few works have been conducted yet to the best of our knowledge. The authors of [21] inpaint an all-in-focus image and propagate it to the light field represented as a focal stack (i.e. set of refocused images) instead of processing directly the light field views.…”

Section: Related Work Light Field Inpaintingmentioning

confidence: 99%

Light Field Inpainting Propagation via Low Rank Matrix Completion

Pendu

Jiang

Guillemot

2018

IEEE Trans. on Image Process.

136

View full text Add to dashboard Cite

Building up on the advances in low rank matrix completion, this article presents a novel method for propagating the inpainting of the central view of a light field to all the other views. After generating a set of warped versions of the inpainted central view with random homographies, both the original light field views and the warped ones are vectorized and concatenated into a matrix. Because of the redundancy between the views, the matrix satisfies a low rank assumption enabling us to fill the region to inpaint with low rank matrix completion. To this end, a new matrix completion algorithm, better suited to the inpainting application than existing methods, is also developed in this paper. In its simple form, our method does not require any depth prior, unlike most existing light field inpainting algorithms. The method has then been extended to better handle the case where the area to inpaint contains depth discontinuities. In this case, a segmentation map of the different depth layers of the inpainted central view is required. This information is used to warp the depth layers with different homographies. Our experiments with natural light fields captured with plenoptic cameras demonstrate the robustness of the low rank approach to noisy data as well as large color and illumination variations between the views of the light field.

show abstract

Section: Related Work Light Field Inpaintingmentioning

confidence: 99%

Light Field Inpainting Propagation via Low Rank Matrix Completion

Pendu

Jiang

Guillemot

2018

IEEE Trans. on Image Process.

136

View full text Add to dashboard Cite

show abstract

“…A considerable amount of researches focused on depth from focus control for decades [3][4][5][6][7][8]. Most of these methods concentrated on depth from focus/defocus or depth recovery from the focal stack on light field cameras [4,5,9,10]. Using light field cameras has an advantage of capturing simultaneous multiple views with variable focal points which provide more accurate information about the depth of the scene; however, the images are captured in low resolution and in small aperture the value of Signal-to-noise ratio (SNR) is significantly low [4].…”

Section: Previous Workmentioning

confidence: 99%

“…The size of these cameras along with the mentioned challenges makes them inapplicable for handheld devices such as smartphones. Another disadvantage of light field cameras is the disability in handling occlusion due to the lack of lateral variation being captured in different viewpoints [9].…”

Section: Previous Workmentioning

confidence: 99%

Application of preconditioned alternating direction method of multipliers in depth from focal stack

Javidnia

Corcoran

2018

J. Electron. Imag.

View full text Add to dashboard Cite

Post capture refocusing effect in smartphone cameras is achievable by using focal stacks. However, the accuracy of this effect is totally dependent on the combination of the depth layers in the stack. The accuracy of the extended depth of field effect in this application can be improved significantly by computing an accurate depth map which has been an open issue for decades. To tackle this issue, in this paper, a framework is proposed based on Preconditioned Alternating Direction Method of Multipliers (PADMM) for depth from the focal stack and synthetic defocus application. In addition to its ability to provide high structural accuracy and occlusion handling, the optimization function of the proposed method can, in fact, converge faster and better than state of the art methods. The evaluation has been done on 21 sets of focal stacks and the optimization function has been compared against 5 other methods. Preliminary results indicate that the proposed method has a better performance in terms of structural accuracy and optimization in comparison to the current state of the art methods.

show abstract

“…To enhance visual quality, many approaches have been proposed [8,28,18,6,20,7] to remove the aliasing effects based on view interpolation [6], depth-based filtering [5], or multi-scale fusion [28]. However, since most of them rely on depth estimations [19,4], inaccurate depth maps will cause severe degradation in anti-aliasing performance. Moreover, existing methods aim at removing aliasing artefacts from an individual refocused image, which is corresponding to a specific depth layer in the whole focal stack.…”

Section: Introductionmentioning

confidence: 99%

Deep Anti-Aliasing of Whole Focal Stack Using Slice Spectrum

Li¹,

Wang²,

Zhu³

et al. 2021

IEEE Trans. Comput. Imaging

View full text Add to dashboard Cite

The paper aims at removing the aliasing effects for the whole focal stack generated from a sparse 3D light field, while keeping the consistency across all the focal layers. We first explore the structural characteristics embedded in the focal stack slice and its corresponding frequency-domain representation, i.e., the focal stack spectrum (FSS). We also observe that the energy distribution of FSS always locates within the same triangular area under different angular sampling rates, additionally the continuity of point spread function (PSF) is intrinsically maintained in the FSS. Based on these two findings, we propose a learning-based FSS reconstruction approach for one-time aliasing removing over the whole focal stack. What's more, a novel conjugate-symmetric loss function is proposed for the optimization. Compared to previous works, our method avoids an explicit depth estimation, and can handle challenging large-disparity scenarios. Experimental results on both synthetic and real light field datasets show the superiority of the proposed approach for different scenes and various angular sampling rates.

show abstract

Light field completion using focal stack propagation

Cited by 10 publications

References 4 publications

Light Field Inpainting Propagation via Low Rank Matrix Completion

Light Field Inpainting Propagation via Low Rank Matrix Completion

Application of preconditioned alternating direction method of multipliers in depth from focal stack

Deep Anti-Aliasing of Whole Focal Stack Using Slice Spectrum

Contact Info

Product

Resources

About