Accurate Image-Guided Stereo Matching With Efficient Matching Cost and Disparity Refinement

Zhan, Yunlong; Gu, Yuzhang; Huang, Kui; Zhang, Cheng; Hu, Keli

doi:10.1109/tcsvt.2015.2473375

Cited by 88 publications

(36 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method [49] is similar to ours in terms of multi-scale cost-volume utilization, but its purpose is to improve the quality of the disparity maps, not to reduce the computational complexity. Recently, Zhan et al [48] proposed some techniques for local stereo matching methods to improve the accuracy: mask filtering as a pre-processing, an improved matching cost function, and multi-step disparity refinement as a post-processing. Inspired by the great success of convolutional neural networks (CNNs) in image recognition task, CNNs are recently used for computing the label costs (matching costs in stereo matching and optical flow estimation) instead of hand-crafted cost functions [11,13,23,46,47], which has led to significant improvement in terms of accuracy.…”

Section: Cost Aggregation Methods For Labeling Problemsmentioning

confidence: 99%

Efficiency-enhanced cost-volume filtering featuring coarse-to-fine strategy

Furuta

Ikehata

Yamaskai

et al. 2017

Multimed Tools Appl

View full text Add to dashboard Cite

Cost-volume filtering (CVF) is one of the most widely used techniques for solving general multi-labeling problems based on a Markov random field (MRF). However it is inefficient when the label space size (i.e., the number of labels) is large. This paper presents a coarse-to-fine strategy for cost-volume filtering that efficiently and accurately addresses multi-labeling problems with a large label space size. Based on the observation that true labels at the same coordinates in images of different scales are highly correlated, we truncate unimportant labels for cost-volume filtering by leveraging the labeling output of lower scales. Experimental results show that our algorithm achieves much higher efficiency than the original CVF method while maintaining a comparable level of accuracy. Although we performed experiments that deal with only stereo matching and optical flow estimation, the proposed method can be employed in many other applications because of the applicability of CVF to general discrete pixel-labeling problems based on an MRF.

show abstract

Section: Cost Aggregation Methods For Labeling Problemsmentioning

confidence: 99%

Efficiency-enhanced cost-volume filtering featuring coarse-to-fine strategy

Furuta

Ikehata

Yamaskai

et al. 2017

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…The 4 th ranked method KADI [47] presents a two-phase strategy for combining separate cost volumes, a mean-shift segmentation-driven approach for handling disparity outliers and disparity histogram analysis for fostering low-textured area plane fitting. Notice that [50] was under review at the time of this paper's writing. Therefore, the proposed method ranks 4 th among already published methods.…”

Section: B Middlebury Online Stereo Evaluation Benchmarkmentioning

confidence: 99%

Content-Based Guided Image Filtering, Weighted Semi-Global Optimization, and Efficient Disparity Refinement for Fast and Accurate Disparity Estimation

Kordelas

Alexiadis

Daras

et al. 2016

IEEE Trans. Multimedia

View full text Add to dashboard Cite

This paper presents a novel approach, which relies on content-based guided image filtering and weighted semi-global optimization for fast and accurate disparity estimation. Initially, the approach uses a pixel-based cost term that combines gradient, Gabor-Feature and color information. The pixel-based matching costs are filtered by applying guided image filtering, which relies on rectangular support windows of two different sizes. In this way, two filtered costs are estimated for each pixel. Among the two filtered costs, the one that will be finally assigned to each pixel, depends on the local image content around this pixel. The filtered cost volume is further refined by exploiting weighted semi-global optimization, which improves the disparity estimation accuracy. Finally, the disparity refinement in outlier regions relies on a straightforward and time efficient outliers handling scheme and on a simple approach which deals with the disparity outliers at depth discontinuities. Experimental results on the Middlebury online stereo evaluation benchmark and 27 additional Middlebury stereo pairs, prove that our method is able to generate disparity maps with high accuracy while keeping the computational cost low.

show abstract

“…Usually it is difficult to obtain full-FoV depth by traditional stereo-matching methods [1,2]. This kind of method can be formulated as a three-step pipeline including matching cost calculation [3], cost aggregation/optimization [4,5], and disparity refinement [6,7].…”

Section: Introductionmentioning

confidence: 99%

Robust Full-Fov Depth Estimation in Tele-Wide Camera System

Guo

Song

Chang

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Tele-wide camera system with different Field of View (FoV) lenses becomes very popular in recent mobile devices. Usually it is difficult to obtain full-FoV depth based on traditional stereo-matching methods. Pure Deep Neural Network (DNN) based depth estimation methods can obtain full-FoV depth, but have low robustness for scenarios which are not covered by training dataset. In this paper, to address the above problems we propose a hierarchical hourglass network for robust full-FoV depth estimation in tele-wide camera system, which combines the robustness of traditional stereo-matching methods with the accuracy of DNN. More specifically, the proposed network comprises three major modules: single image depth prediction module infers initial depth from input color image, depth propagation module propagates traditional stereo-matching tele-FoV depth to surrounding regions, and depth combination module fuses the initial depth with the propagated depth to generate final output. Each of these modules employs an hourglass model, which is a kind of encoderdecoder structure with skip connections. Experimental results compared with state-of-the-art depth estimation methods demonstrate that our method not only produces robust and better subjective depth quality on wild test images, but also obtains better quantitative results on standard datasets.Index Terms-Depth estimation, Hierarchical hourglass network, L1-norm scale-invariant loss function, Tele-wide camera, Full field of view.

show abstract

Accurate Image-Guided Stereo Matching With Efficient Matching Cost and Disparity Refinement

Cited by 88 publications

References 35 publications

Efficiency-enhanced cost-volume filtering featuring coarse-to-fine strategy

Efficiency-enhanced cost-volume filtering featuring coarse-to-fine strategy

Content-Based Guided Image Filtering, Weighted Semi-Global Optimization, and Efficient Disparity Refinement for Fast and Accurate Disparity Estimation

Robust Full-Fov Depth Estimation in Tele-Wide Camera System

Contact Info

Product

Resources

About