Accurate Depth and Normal Maps from Occlusion-Aware Focal Stack Symmetry

Strecke, Michael; Alperovich, Anna; Goldluecke, Bastian

doi:10.1109/cvpr.2017.271

Cited by 47 publications

(40 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section we provide the comparison of the proposed method with presented in Section 2 state-of-the-art algorithms [35,28,25,26,17,31,16,30]. In tables and figures these algorithms are presented under acronyms SPO, OFSY, RM3DE, SC GC, EPI1, EPI2, LF and LF OCC respectively.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Fast and Efficient Depth Map Estimation from Light Fields

Anisimov

Stricker

2017

2017 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

The paper presents an algorithm for depth map estimation from the light field images in relatively small amount of time, using only single thread on CPU. The proposed method improves existing principle of line fitting in 4dimensional light field space. Line fitting is based on color values comparison using kernel density estimation. Our method utilizes result of Semi-Global Matching (SGM) with Census transform-based matching cost as a border initialization for line fitting. It provides a significant reduction of computations needed to find the best depth match. With the suggested evaluation metric we show that proposed method is applicable for efficient depth map estimation while preserving low computational time compared to others.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Results for "dino" dataset from [15]. (a) Ground truth, (b) SPO [35], OFSY [28], (d) RM3DE [25], (e) SC GC [26], (f) EPI1 [17], (g) EPI2 [31], (h) LF [16] Table 2. Runtime in seconds on 4D Light Field Benchmark [15] better than in most of the state-of-the-art algorithms.…”

Section: Algorithm Settingsmentioning

confidence: 99%

Fast and Efficient Depth Map Estimation from Light Fields

Anisimov

Stricker

2017

2017 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

show abstract

“…Our method is evaluated with the 4-dimensional Light Field Benchmark [8], [9]. We provide a comparison of the proposed algorithm with the state-of-the-art methods presented in Section II-A: BSL [11], EPI1 [16], EPI2 [13], EPINET [27], LF [20], LF OCC [15], OFSY [38], RM3DE [18], RPRF [22]. Together with that, qualitative results for real-world EPFL [40] and Middlebury datasets [41], [42] are presented.…”

Section: Methodsmentioning

confidence: 99%

“…Ground truth BSL [11] EPI1 [16] EPI2 [13] EPINET [27] LF [20] LF OCC [15] OFSY [38] RM3DE [18] RPRF [22] FSL (ours) 1, D H (p)−1]| 3. If the disparity value does not satisfy these conditions, then D n (p) = D f (p) After this step we apply a median filter to D n in order to remove the impulse noise.…”

Section: Original Imagementioning

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

“…The resulting feature maps are concatenated and combined using 1 × 1 convolutions for later processing. In fact, it has been shown that using selected angular directions is beneficial in the context of depth estimation [15], [50].…”

Section: B Lfnet Variantsmentioning

confidence: 99%

Light Field Saliency Detection With Deep Convolutional Networks

Zhang

Liu

Zhang

et al. 2020

IEEE Trans. on Image Process.

108

View full text Add to dashboard Cite

CNN-based methods have been proven to work well for saliency detection on RGB images owing to the outstanding feature representation abilities of CNNs. However, their performance will degrade when detecting multiple saliency regions in highly cluttered or similar backgrounds. To address these problems, in this paper we resort to light field imaging, which records the color intensity of each pixel as well as the directions of incoming light rays, and thus can improve performance for saliency detection owing to the usage of both spatial and angular patterns encoded in light field images. However, it is not trivial to use CNN-based methods for saliency detection on light field images because these methods are not specifically designed for processing light field inputs and current light field datasets are not sufficiently large to train CNNs. To overcome these issues, we first present a new Lytro Illum dataset, which contains 640 light fields and their corresponding micro-lens images, central-viewing images as well as ground-truth saliency maps. Comparing to the current light field saliency datasets [1], [2], the new dataset is larger, of higher quality, contains more variations and more types of light field inputs, which is suitable for training deeper networks as well as better benchmarking algorithms. Furthermore, we propose a novel end-to-end CNNbased framework for light field saliency detection as well as its several variants. We systematically study the impact of different variants and compare light field saliency with regular 2D saliency on the performance of the proposed network. We also conduct extensive experimental comparisons, which indicate that our network significantly outperforms state-of-the-art methods on the proposed dataset and has desired generalization abilities on other existing datasets.

show abstract

Accurate Depth and Normal Maps from Occlusion-Aware Focal Stack Symmetry

Cited by 47 publications

References 27 publications

Fast and Efficient Depth Map Estimation from Light Fields

Fast and Efficient Depth Map Estimation from Light Fields

Rapid Light Field Depth Estimation with Semi-Global Matching

Light Field Saliency Detection With Deep Convolutional Networks

Contact Info

Product

Resources

About