Search

In this paper, we tackle depth estimation and blur removal from a single out-of-focus image. Previously, depth is estimated, and blurred is removed using multiple images; for example, from multiview or stereo scenes, but doing so with a single image is challenging. Earlier works of monocular images for depth estimated and deblurring either exploited geometric characteristics or priors using hand-crafted features. Lately, there is enough evidence that deep convolutional neural networks (CNN) significantly improved numerous vision applications; hence, in this article, we present a depth estimation method that leverages rich representations learned from cascaded convolutional and fully connected neural networks operating on a patch-pooled set of feature maps. Furthermore, from this depth, we computationally reconstruct an all-focus image, i.e., removing the blur and achieve synthetic re-focusing, all from a single image. Our method is fast, and it substantially improves depth accuracy over the state-of-the-art alternatives. Our proposed depth estimation approach can be utilized for everyday scenes without any geometric priors or extra information. Furthermore, our experiments on two benchmark datasets consist images of indoor and outdoor scenes, i.e., Make3D and NYU-v2 demonstrate superior performance in comparison with other available depth estimation state-of-the-art methods by reducing the root-mean-squared error by 57% and 46%, and state-of-the-art blur removal methods by 0.36 dB and 0.72 dB in PSNR, respectively. This improvement in-depth estimation and deblurring is further demonstrated by the superior performance using real defocus images against images captured with a prototype lens. [ABSTRACT FROM AUTHOR]

Global or indirect illumination effects such as interreflections and subsurface scattering severely degrade the performance of structured light-based 3D scanning. In this paper, we analyze the errors in structured light, caused by both long-range (interreflections) and short-range (subsurface scattering) indirect illumination. The errors depend on the frequency of the projected patterns, and the nature of indirect illumination. In particular, we show that long-range effects cause decoding errors for low-frequency patterns, whereas short-range effects affect high-frequency patterns. Based on this analysis, we present a practical 3D scanning system which works in the presence of a broad range of indirect illumination. First, we design binary structured light patterns that are resilient to individual indirect illumination effects using simple logical operations and tools from combinatorial mathematics. Scenes exhibiting multiple phenomena are handled by combining results from a small ensemble of such patterns. This combination also allows detecting any residual errors that are corrected by acquiring a few additional images. Our methods can be readily incorporated into existing scanning systems without significant overhead in terms of capture time or hardware. We show results for several scenes with complex shape and material properties. [ABSTRACT FROM AUTHOR]

A new depth estimation method for 3D reconstruction in a synthetic aperture integral imaging framework is presented. This method removes the edges of the objects in the elemental images when the objects are in focus. This strategy aims to compensate for the noise that objects focused close to the cameras can introduce into the photo-consistency measure of objects at higher depths. Furthermore, a photo-consistency criterion is applied combining a defocus and a correspondence measure, and a depth regularization method which smooths noisy depth results for the case of object surfaces. The proposed method obtains consistent results for any type of object surfaces as well as very sharp boundaries. Experimental results show that our method reduces the noise in the object edges and gives rise to an improvement in the depth map results in relation to the other methods shown in the comparative analysis. [ABSTRACT FROM AUTHOR]

This article discusses a depth prediction model that takes advantage of rich interpretations. Profundity assessment is a basic interest for scene understanding and exact 3D reproduction. Latest methodologies with profound learning exploit mathematical designs of standard sharp pictures to foresee profundity maps. In any case, cameras can likewise deliver pictures with defocus obscure contingent upon the profundity of the articles and camera settings. Subsequently, these highlights might address a significant clue for figuring out how to foresee profundity. In this article, we postulate a full framework for single-picture profundity expectation by estimating the level of obscure w.r.t real profundity by bringing the picture in to concentrate just on pre-characterized focal point numbers. As a result, these characteristics may provide a crucial clue for studying to predict depth. These lens numbers indicate the distance at which the lens is currently focused. We also intend to know the influence of lens aperture numbers on the depth estimated. For this stated goal,We introduce a new data set that has 477 images taken in real-time using a DSLR (Digital Single-Lens Reflex). For indoor pictures, a lens is coupled with ground truth depth data provided with a laser distance meter.On this new platform, the strategy has been a framework that supports new data set and is proved that the predicted depth estimates correlate with ground truth by 98.7 percent with an 8.647 Std Error estimate. When compared to recent research on stereo vision and other non-triangulation techniques proposed so far, the depth estimations derived from the proposed model approximates the ground truth with RMSE of 0.05 and display around 98.7 percent correlation wrt ground truth data. Depth estimation strategy using a Single RGB cameras are proved efficient in computing depth estimates from blur with 99 percent accuracy, which is not in an earlier case. Our proposed model evidently works well with both sharp and blur images in computing depth estimates up to 3.3 meters range irrespective of whether an image is in focus or out of focus. [ABSTRACT FROM AUTHOR]

We present the focal flow sensor. It is an unactuated, monocular camera that simultaneously exploits defocus and differential motion to measure a depth map and a 3D scene velocity field. It does this using an optical-flow-like, per-pixel linear constraint that relates image derivatives to depth and velocity. We derive this constraint, prove its invariance to scene texture, and prove that it is exactly satisfied only when the sensor’s blur kernels are Gaussian. We analyze the inherent sensitivity of the focal flow cue, and we build and test a prototype. Experiments produce useful depth and velocity information for a broader set of aperture configurations, including a simple lens with a pillbox aperture. [ABSTRACT FROM AUTHOR]

We present confocal stereo, a new method for computing 3D shape by controlling the focus and aperture of a lens. The method is specifically designed for reconstructing scenes with high geometric complexity or fine-scale texture. To achieve this, we introduce the confocal constancy property, which states that as the lens aperture varies, the pixel intensity of a visible in-focus scene point will vary in a scene- independent way, that can be predicted by prior radiometric lens calibration. The only requirement is that incoming radiance within the cone subtended by the largest aperture is nearly constant. First, we develop a detailed lens model that factors out the distortions in high resolution SLR cameras (12MP or more) with large-aperture lenses (e.g., f1.2). This allows us to assemble an A× F aperture-focus image (AFI) for each pixel, that collects the undistorted measurements over all A apertures and F focus settings. In the AFI representation, confocal constancy reduces to color comparisons within regions of the AFI, and leads to focus metrics that can be evaluated separately for each pixel. We propose two such metrics and present initial reconstruction results for complex scenes, as well as for a scene with known ground-truth shape. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]