Reconstructing a 3-D depth map from one or more images

Several algorithms are suggested for recovering depth and orientation maps of a surface from its image intensities. They combine the advantages of stereo vision and shape-from-shading (SFS) methods. These algorithms generate accurate, unambiguous and dense surface depth and orientation maps. Most of the existing SFS algorithms cannot be directly extended to combine stereo images because the recovery of surface depth and that of orientation are separated in these formulations. We first present an SFS algorithm that couples the generation of depth and orientation maps. This formulation also ensures that the reconstructed surface depth and its orientation are consistent. The SFS algorithm for a single image is then extended to utilize stereo images. The correspondence over stereo images is established simultaneously with the generation of surface depth and orientation. An alternative approach is also suggested for combining stereo and SFS techniques. This approach can be used to combine needle maps which are directly available from other sources such as photometric stereo. Finally we present an algorithm to combine sparse depth measurements with an orientation map to reconstruct a surface. The same algorithm can be combined with the above algorithms for solving the SFS problem with sparse depth measurements. Thus various information sources can be used to accurately reconstruct a surface.     

Massively parallel GPU computing for fast stereo correspondence algorithms

Current accurate stereo matching algorithms employ some key techniques that are not suitable for parallel GPU architecture. It will be tricky and cumbersome to directly take these techniques into GPU applications. Trying to tackle this difficulty, we design two GPU-based stereo matching algorithms, one using a local fixed aggregation window whose size is configurable, and the other using an adaptive aggregation window which only includes necessary pixels. We use the winner-takes-all (WTA) principle for optimization and a plain voting refinement for post-processing; both do not need complex data structures. We aim to implement on GPU platforms fast stereo matching algorithms that produce results with same-level quality as other WTA local dense methods that use window-based cost aggregation. In our GPU-based implementation of the fixed window partially demosaiced CFA stereo matching application, accelerations up to 20 times are obtained for large size images. In our GPU-based implementation of the adaptive window color stereo matching application, experiment results show that it can handle four pairs of standard images from Middlebury database within roughly 100 ms.     

Generalised residual images’ effect on illumination artifact removal for correspondence algorithms

The intensity (grey value) consistency of image pixels in a sequence or stereo camera setup is of central importance to numerous computer vision applications. Most stereo matching and optical flow algorithms minimise an energy function composed of a data term and a regularity or smoothing term. To date, well performing methods rely on the intensity consistency of the image pixel values to model the data term. Such a simple model fails if the illumination is (even slightly) different between the input images. Amongst other situations, this may happen due to background illumination change over the sequence, different reflectivity of a surface, vignetting, or shading effects.In this paper, we investigate the removal of illumination artifacts and show that generalised residual images substantially improve the accuracy of correspondence algorithms. In particular, we motivate the concept of residual images and show two evaluation approaches using either ground truth correspondence fields (for stereo matching and optical flow algorithms) or errors based on a predicted view (for stereo matching algorithms).     

Virtual stereo content rendering technology review for light-field display

Light field display (LFD) is considered as a promising technology to reconstruct the light rays’ distribution of the real 3D scene, which approximates the original light field of target displayed objects with all depth cues in human vision including binocular disparity, motion parallax, color hint and correct occlusion relationship. Currently, computer-generated content is widely used for the LFD system, therefore rich 3D content can be provided. This paper firstly introduces applications of light field technologies in display system. Additionally, virtual stereo content rendering techniques and their application scenes are thoroughly combed and pointed out its pros and cons. Moreover, according to the different characteristics of light field system, the coding and correction algorithms in virtual stereo content rendering techniques are reviewed. Through the above discussion, there are still many problems in the existing rendering techniques for LFD. New rendering algorithms should be introduced to solve the real-time light-field rendering problem for large-scale virtual scenes.     

Multiflash stereopsis: depth-edge-preserving stereo with small baseline illumination

Traditional stereo matching algorithms are limited in their ability to produce accurate results near depth discontinuities, due to partial occlusions and violation of smoothness constraints. In this paper, we use small baseline multi-flash illumination to produce a rich set of feature maps that enable acquisition of discontinuity preserving point correspondences. First, from a single multi-flash camera, we formulate a qualitative depth map using a gradient domain method that encodes object relative distances. Then, in a multiview setup, we exploit shadows created by light sources to compute an occlusion map. Finally, we demonstrate the usefulness of these feature maps by incorporating them into two different dense stereo correspondence algorithms, the first based on local search and the second based on belief propagation. Experimental results show that our enhanced stereo algorithms are able to extract high quality, discontinuity preserving correspondence maps from scenes that are extremely challenging for conventional stereo methods. We also demonstrate that small baseline illumination can be useful to handle specular reflections in stereo imagery. Different from most existing active illumination techniques, our method is simple, inexpensive, compact, and requires no calibration of light sources.     

三维视觉前沿进展

在自动驾驶、机器人、数字城市以及虚拟/混合现实等应用的驱动下,三维视觉得到了广泛的关注。三维视觉研究主要围绕深度图像获取、视觉定位与制图、三维建模及三维理解等任务而展开。本文围绕上述三维视觉任务,对国内外研究进展进行了综合评述和对比分析。首先,针对深度图像获取任务,从非端到端立体匹配、端到端立体匹配及无监督立体匹配3个方面对立体匹配研究进展进行了回顾,从深度回归网络和深度补全网络两个方面对单目深度估计研究进展进行了回顾。其次,针对视觉定位与制图任务,从端到端视觉定位和非端到端视觉定位两个方面对大场景下的视觉定位研究进展进行了回顾,并从视觉同步定位与地图构建和融合其他传感器的同步定位与地图构建两个方面对同步定位与地图构建的研究进展进行了回顾。再次,针对三维建模任务,从深度三维表征学习、深度三维生成模型、结构化表征学习与生成模型以及基于深度学习的三维重建等4个方面对三维几何建模研究进展进行了回顾,并从多视RGB重建、单深度相机和多深度相机方法以及单视图RGB方法等3个方面对人体动态建模研究进展进行了回顾。最后,针对三维理解任务,从点云语义分割和点云实例分割两个方面对点云语义理解研究进展进行了回顾。在此基础上,给出了三维视觉研究的未来发展趋势,旨在为相关研究者提供参考。     

Probabilistic fusion of stereo with color and contrast for bilayer segmentation

This paper describes models and algorithms for the real-time segmentation of foreground from background layers in stereo video sequences. Automatic separation of layers from color/contrast or from stereo alone is known to be error-prone. Here, color, contrast, and stereo matching information are fused to infer layers accurately and efficiently. The first algorithm, layered dynamic programming (LDP), solves stereo in an extended six-state space that represents both foreground/background layers and occluded regions. The stereo-match likelihood is then fused with a contrast-sensitive color model that is learned on-the-fly and stereo disparities are obtained by dynamic programming. The second algorithm, layered graph cut (LGC), does not directly solve stereo. Instead, the stereo match likelihood is marginalized over disparities to evaluate foreground and background hypotheses and then fused with a contrast-sensitive color model like the one used in LDP. Segmentation is solved efficiently by ternary graph cut. Both algorithms are evaluated with respect to ground truth data and found to have similar performance, substantially better than either stereo or color/contrast alone. However, their characteristics with respect to computational efficiency are rather different. The algorithms are demonstrated in the application of background substitution and shown to give good quality composite video output.     

Stereo Matching with Nonlinear Diffusion

One of the central problems in stereo matching (and other image registration tasks) is the selection of optimal window sizes for comparing image regions. This paper addresses this problem with some novel algorithms based on iteratively diffusing support at different disparity hypotheses, and locally controlling the amount of diffusion based on the current quality of the disparity estimate. It also develops a novel Bayesian estimation technique, which significantly outperforms techniques based on area-based matching (SSD) and regular diffusion. We provide experimental results on both synthetic and real stereo image pairs.     

Depth from Defocus vs. Stereo: How Different Really Are They?

Depth from Focus (DFF) and Depth from Defocus (DFD) methods are theoretically unified with the geometric triangulation principle. Fundamentally, the depth sensitivities of DFF and DFD are not different than those of stereo (or motion) based systems having the same physical dimensions. Contrary to common belief, DFD does not inherently avoid the matching (correspondence) problem. Basically, DFD and DFF do not avoid the occlusion problem any more than triangulation techniques, but they are more stable in the presence of such disruptions. The fundamental advantage of DFF and DFD methods is the two-dimensionality of the aperture, allowing more robust estimation. We analyze the effect of noise in different spatial frequencies, and derive the optimal changes of the focus settings in DFD. These results elucidate the limitations of methods based on depth of field and provide a foundation for fair performance comparison between DFF/DFD and shape from stereo (or motion) algorithms.     

A cost-benefit analysis of a third camera for stereo correspondence

This paper looks at the twin issues of the gain in accuracy of stereo correspondence and the accompanying increase in computational cost due to the use of a third camera for stereo analysis. Trinocular stereo algorithms differ from binocular algorithms essentially in the epipolar constraint used in the local matching stage. The current literature does not provide any insight into the relative merits of binocular and trinocular stereo matching with the matching accuracy being verified aginst the ground truth. Experiments for evaluating the relative performance of binocular and trinocular stereo algorithms were conducted. The stereo images used for the performance evaluation were generated by applying a Lambertian reflectance model to real Digital Elevation Maps (DEMs) available from the U.S. Geological Survey. The matching accuracy of the stereo algorithms was evaluated by comparing the observed stereo disparity against the ground truth derived from the DEMs. It was observed that trinocular local matching reduced the percentage of mismatches having large disparity errors by more than half when compared to binocular matching. On the other hand, trinocular stereopsis increased the computational cost of local matching over binocular by only about one-fourth. We also present a quantization-error analysis of the depth reconstruction process for the nonparallel stereo-imaging geometry used in our experiments.     

Hierarchical stereo and motion correspondence using feature groupings

Hierarchical feature based stereo matching and motion correspondence algorithms are presented. The hierarchy consists of lines, vertices, edges and surfaces. Matching starts at the highest level of the hierarchy (surfaces) and proceeds to the lowest (lines). Higher level features are easier to match, because they are fewer in number and more distinct in form. These matches then constrain the matches at lower levels. Perceptual and structural relations are used to group matches into islands of certainty. A Truth Maintenance System (TMS) is used to enforce grouping constraints and eliminate inconsistent match groupings. The TMS is also used to carry out belief revisions necessitiated by additions, deletions and confirmations of feature and match hypotheses.The support of Defense Advanced Research Projects Agency (ARPA Order No. 8979) and the U.S. Army Engineer Topographic Laboratories under contract DACA 76-92-C-0024 is gratefully acknowledged.     

Estimating optimal parameters for MRF stereo from a single image pair

This paper presents a novel approach for estimating the parameters for MRF-based stereo algorithms. This approach is based on a new formulation of stereo as a maximum a posterior (MAP) problem in which both a disparity map and MRF parameters are estimated from the stereo pair itself. We present an iterative algorithm for the MAP estimation that alternates between estimating the parameters while fixing the disparity map and estimating the disparity map while fixing the parameters. The estimated parameters include robust truncation thresholds for both data and neighborhood terms, as well as a regularization weight. The regularization weight can be either a constant for the whole image or spatially-varying, depending on local intensity gradients. In the latter case, the weights for intensity gradients are also estimated. Our approach works as a wrapper for existing stereo algorithms based on graph cuts or belief propagation, automatically tuning their parameters to improve performance without requiring the stereo code to be modified. Experiments demonstrate that our approach moves a baseline belief propagation stereo algorithm up six slots in the Middlebury rankings     

Direct recovery of three-dimensional scene geometry from binocularstereo disparity

An analysis of disparity is presented. It makes explicit the geometric relations between a stereo disparity field and a differentially project scene. These results show how it is possible to recover three-dimensional surface geometry through first-order (i.e., distance and orientation of a surface relative to an observer) and binocular viewing parameters in a direct fashion from stereo disparity. As applications of the analysis, algorithms have been developed for recovering three-dimensional surface orientation and discontinuities from stereo disparity. The results of applying these algorithms to natural image binocular stereo disparity information are presented     

Stereo vision for robotic applications in the presence of non-ideal lighting conditions

Many robotic and machine-vision applications rely on the accurate results of stereo correspondence algorithms. However, difficult environmental conditions, such as differentiations in illumination depending on the viewpoint, heavily affect the stereo algorithms’ performance. This work proposes a new illumination-invariant dissimilarity measure in order to substitute the established intensity-based ones. The proposed measure can be adopted by almost any of the existing stereo algorithms, enhancing it with its robust features. The performance of the dissimilarity measure is validated through experimentation with a new adaptive support weight (ASW) stereo correspondence algorithm. Experimental results for a variety of lighting conditions are gathered and compared to those of intensity-based algorithms. The algorithm using the proposed dissimilarity measure outperforms all the other examined algorithms, exhibiting tolerance to illumination differentiations and robust behavior.     

Adaptive disparity computation using local and non-local cost aggregations

A new method is proposed to adaptively compute the disparity of stereo matching by choosing one of the alternative disparities from local and non-local disparity maps. The initial two disparity maps can be obtained from state-of-the-art local and non-local stereo algorithms. Then, the more reasonable disparity is selected. We propose two strategies to select the disparity. One is based on the magnitude of the gradient in the left image, which is simple and fast. The other utilizes the fusion move to combine the two proposal labelings (disparity maps) in a theoretically sound manner, which is more accurate. Finally, we propose a texture-based sub-pixel refinement to refine the disparity map. Experimental results using Middlebury datasets demonstrate that the two proposed selection strategies both perform better than individual local or non-local algorithms. Moreover, the proposed method is compatible with many local and non-local algorithms that are widely used in stereo matching.     

根据灰度值信息自适应窗口的半全局匹配

目的 立体匹配算法是立体视觉研究的关键点,算法的匹配精度和速度直接影响3维重建的效果。对于传统立体匹配算法来说,弱纹理区域、视差深度不连续区域和被遮挡区域的匹配精度依旧不理想,为此选择具有全局匹配算法和局部匹配算法部分优点、性能介于两种算法之间、且鲁棒性强的半全局立体匹配算法作为研究内容,提出自适应窗口与半全局立体匹配算法相结合的改进方向。方法 以通过AD（absolute difference）算法求匹配代价的半全局立体匹配算法为基础,首先改变算法匹配代价的计算方式,研究窗口大小对算法性能的影响,然后加入自适应窗口算法,研究自适应窗口对算法性能的影响,最后对改进算法进行算法性能评价与比较。结果 实验结果表明,匹配窗口的选择能够影响匹配算法性能、提高算法的适用范围,自适应窗口的加入能够提高算法匹配精度特别是深度不连续区域的匹配精度,并有效降低算法运行时间,对Cones测试图像集,改进的算法较改进前误匹配率在3个测试区域平均减少2.29%;对于所有测试图像集,算法运行时间较加入自适应窗口前平均减少28.5%。结论 加入自适应窗口的半全局立体匹配算法具有更优的算法性能,能够根据应用场景调节算法匹配精度和匹配速度。     

Multiple paths extraction in images using a constrained expanded trellis

Single shortest path extraction algorithms have been used in a number of areas such as network flow and image analysis. In image analysis, shortest path techniques can be used for object boundary detection, crack detection, or stereo disparity estimation. Sometimes one needs to find multiple paths as opposed to a single path in a network or an image where the paths must satisfy certain constraints. In this paper, we propose a new algorithm to extract multiple paths simultaneously within an image using a constrained expanded trellis (CET) for feature extraction and object segmentation. We also give a number of application examples for our multiple paths extraction algorithm.     

An FPGA stereo matching unit based on fuzzy logic

Stereo matching is one of the most used algorithms in real-time image processing applications such as positioning systems for mobile robots, three-dimensional building mapping and recognition, detection and three-dimensional reconstruction of objects. In order to improve the performance, stereo matching algorithms often have been implemented in dedicated hardware such as FPGA or GPU devices. In this paper an FPGA stereo matching unit based on fuzzy logic is described. The proposed algorithm consists of three stages. First, three similarity parameters inherent to each pixel contained in the input stereo pair are computed. Then, the similarity parameters are sent to a fuzzy inference system which determines a fuzzy-similarity value. Finally, the disparity value is defined as the index which maximizes the fuzzy-similarity values (zero up to d_max). Dense disparity maps are computed at a rate of 76 frames per second for input stereo pairs of 1280 × 1024 pixel resolution and a maximum expected disparity equal to 15. The developed FPGA architecture provides reduction of the hardware resource demand compared to other FPGA-based stereo matching algorithms: near to 72.35% for logic units and near to 32.24% for bits of memory. In addition, the developed FPGA architecture increases the processing speed: near to 34.90% pixels per second and outperforms the accuracy of most of real-time stereo matching algorithms in the state of the art.     

A 3D Imaging Framework Based on High-Resolution Photometric-Stereo and Low-Resolution Depth

This paper introduces a 3D imaging framework that combines high-resolution photometric stereo and low-resolution depth. Our approach targets imaging scenarios based on either macro-lens photography combined with focal stacking or a large-format camera that are able to image objects with more than 600 samples per mm $^2$ . These imaging techniques allow photometric stereo algorithms to obtain surface normals at resolutions that far surpass corresponding depth values obtained with traditional approaches such as structured-light, passive stereo, or depth-from-focus. Our work offers two contributions for 3D imaging based on these scenarios. The first is a multi-resolution, patched-based surface reconstruction scheme that can robustly handle the significant resolution difference between our surface normals and depth samples. The second is a method to improve the initial normal estimation by using all the available focal information for images obtained using a focal stacking technique.     

A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

Stereo matching is one of the most active research areas in computer vision. While a large number of algorithms for stereo correspondence have been developed, relatively little work has been done on characterizing their performance. In this paper, we present a taxonomy of dense, two-frame stereo methods. Our taxonomy is designed to assess the different components and design decisions made in individual stereo algorithms. Using this taxonomy, we compare existing stereo methods and present experiments evaluating the performance of many different variants. In order to establish a common software platform and a collection of data sets for easy evaluation, we have designed a stand-alone, flexible C++ implementation that enables the evaluation of individual components and that can easily be extended to include new algorithms. We have also produced several new multi-frame stereo data sets with ground truth and are making both the code and data sets available on the Web. Finally, we include a comparative evaluation of a large set of today's best-performing stereo algorithms.