Dataset and Pipeline for Multi-view Light-Field Video

Sabater, Neus; Boisson, Guillaume; Vandame, B.; Kerbiriou, Paul; Babon, Frederic; Hog, Matthieu; Gendrot, Remy; Langlois, Tristan; Bureller, Olivier; Schubert, Arno; Allié, Valérie

doi:10.1109/cvprw.2017.221

Cited by 77 publications

(50 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We chose an angular configuration that is similar to the one of real light fields captured by rigs of cameras, such as e.g. in [48] and [49], which respectively provide 5 × 3 and 4 × 4 views. We also use the dataset of [48] to test our method on a real light field sequence: 'Bar'.…”

Section: A Scene Flow Datasetsmentioning

confidence: 99%

Scene Flow Estimation From Sparse Light Fields Using a Local 4D Affine Model

David

Pendu

Guillemot

2020

IEEE Trans. Comput. Imaging

View full text Add to dashboard Cite

In this paper, we address the problem of scene flow estimation from sparsely sampled video light fields. We first propose a local 4D affine model to represent scene flows, taking into account light field epipolar geometry. The model parameters are estimated per cluster in the 4D ray space. They are derived by fitting the model on initial motion and disparity estimates obtained by using 2D dense optical flow estimation techniques. We demonstrate that the model is very effective for estimating scene flows from 2D optical flows. The model regularizes the optical flows and disparity maps, and interpolates disparity variation values in occluded regions. The proposed model allows us to benefit from deep learning-based 2D optical flow estimation methods while ensuring scene flow geometry consistency in the 4 dimensions of the light field.

show abstract

Section: A Scene Flow Datasetsmentioning

confidence: 99%

Scene Flow Estimation From Sparse Light Fields Using a Local 4D Affine Model

David

Pendu

Guillemot

2020

IEEE Trans. Comput. Imaging

View full text Add to dashboard Cite

show abstract

“…Neri et al [18] adaptively combine data term and multi-view stereo with a multi-resolution approach for reducing the complexity of the algorithm. Sabater et al [19] propose a method for real-time depth estimation, using a zero-normalized cross-correlation as an image similarity measurement together with pyramid strategy for coarse-to-fine reconstruction. An approach from Jeon et al [20] utilizes the cost volume from shifted subaperture images with different similarity measurements and further result refinement via Graph Cuts (GC) [21].…”

Section: Related Work a Light Field Processingmentioning

confidence: 99%

Rapid Light Field Depth Estimation with Semi-Global Matching

Anisimov

Wasenmüller

Stricker

2019

2019 IEEE 15th International Conference on Intelligent Computer Communication and Processing (ICCP)

View full text Add to dashboard Cite

Running time of the light field depth estimation algorithms is typically high. This assessment is based on the computational complexity of existing methods and the large amounts of data involved. The aim of our work is to develop a simple and fast algorithm for accurate depth computation. In this context, we propose an approach, which involves Semi-Global Matching for the processing of light field images. It forms on comparison of pixels' correspondences with different metrics in the substantially bounded light field space. We show that our method is suitable for the fast production of a proper result in a variety of light field configurations.

show abstract

“…In the last years, several light field cameras were presented. However, some of them are quite large [9,14] preventing their usage in filigree machines. A famous commercial light field camera are the Lytro [5] and Raytrix [6] cameras.…”

Section: Related Workmentioning

confidence: 99%

“…Such a camera assembly approach is easier and more robust to manufacture compared to micro-lens approaches [5]. It is somewhat similar to the multi-camera light field capturing devices [9]; however, since all of the light field views are captured by a single image sensor, it can be considered as more resilient technology, because cameras synchronization and compensation of single sensors deviations do not need to be performed. The connection of the camera to the computational platform is provided via PCIe interface.…”

Section: Light Field Cameramentioning

confidence: 99%

“…In the state-of-the-art such cameras were already described in detail. However, these systems suffer two major drawbacks: the depth estimation algorithms are not working in real-time but sometimes require hours per image [3]; also, the camera systems are usually very large and thus prevent the practical use in filigree setups [9,14]. In this paper, we propose a new compact light field camera, which is capable to compute depth information in real-time.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Compact Light Field Camera for Real-Time Depth Estimation

Anisimov

Wasenmüller

Stricker

2019

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

Depth cameras are utilized in many applications. Recently light field approaches are increasingly being used for depth computation. While these approaches demonstrate the technical feasibility, they can not be brought into real-world application, since they have both a high computation time as well as a large design. Exactly these two drawbacks are overcome in this paper. For the first time, we present a depth camera based on the light field principle, which provides real-time depth information as well as a compact design.

show abstract

Dataset and Pipeline for Multi-view Light-Field Video

Cited by 77 publications

References 26 publications

Scene Flow Estimation From Sparse Light Fields Using a Local 4D Affine Model

Scene Flow Estimation From Sparse Light Fields Using a Local 4D Affine Model

Rapid Light Field Depth Estimation with Semi-Global Matching

A Compact Light Field Camera for Real-Time Depth Estimation

Contact Info

Product

Resources

About