Hyperspectral photometric stereo for a single capture

Photometric stereo (PST) is a widely used technique of estimating surface normals from an image set. However, it often produces inaccurate results for non-Lambertian surface reflectance. In this study, PST is reformulated as a sparse recovery problem where non-Lambertian errors are explicitly identified and corrected. We show that such a problem can be accurately solved via a greedy algorithm called orthogonal matching pursuit (OMP). The performance of OMP is evaluated on synthesized and real-world datasets: we found that the greedy algorithm is overall more robust to non-Lambertian errors than other state-of-the-art sparse approaches with little loss of efficiency. Along with providing an overview of current methods, novel contributions in this paper are as follows: we propose an alternative sparse formulation for PST; in previous PST studies (Wu et al., Robust photometric stereo via low-rank matrix completion and recovery, 2010), (S. Ikehata et al., Robust photometric stereo using sparse regression, 2012), the surface normal vector and the error vector are treated as two entities and are solved independently. In this study, we convert their formulation into a new canonical form of the sparse recovery problem by combining the two vectors into one large vector in a new “stacked” formulation in this domain. This allows for a large repertoire of existing sparse recovery algorithms to be more straightforwardly applied to the PST problem. In our application of the OMP greedy algorithm, we show that greedy solvers can indeed be applied, with this study supplying the first of such attempt at employing greedy approaches to estimate surface normals within the framework of PST. We numerically compare the performance of several normal vector recovery methods. Most notably, this is the first detailed test on complex images of the normal estimation accuracy of our previously proposed method, least median of squares (LMS).

Photometric stereo is a method to obtain surface normals of an object using its images captured under varying illumination directions. The existing deep learning-based methods require multiple images of an object captured using complex image acquisition systems. In this work, we propose a deep learning framework to perform three tasks jointly: (i) lighting estimation, (ii) image relighting, and (iii) surface normal estimation, all from a single input image of an object with non-Lambertian surface and general reflectance. The network explicitly segregates global geometric features and local lighting-specific features of the object from a single image. The local features resemble attached shadows, shadings, and specular highlights, providing valuable lighting estimation and relighting cues. The global features capture the lighting-independent geometric attributes that effectively guide the surface normal estimation. The joint training transfers valuable insights to achieve significant improvements across all three tasks. We show that the proposed single-image-based relighting framework outperforms several existing photometric stereo methods which require multiple images of a static object.

Deep-learning-based polarization 3D imaging techniques, which train networks in a data-driven manner, are capable of estimating a target’s surface normal distribution under passive lighting conditions. However, existing methods have limitations in restoring target texture details and accurately estimating surface normals. Information loss can occur in the fine-textured areas of the target during the reconstruction process, which can result in inaccurate normal estimation and reduce the overall reconstruction accuracy. The proposed method enables extraction of more comprehensive information, mitigates the loss of texture information during object reconstruction, enhances the accuracy of surface normal estimation, and facilitates more comprehensive and precise reconstruction of objects. The proposed networks optimize the polarization representation input by utilizing the Stokes-vector-based parameter, in addition to separated specular and diffuse reflection components. This approach reduces the impact of background noise, extracts more relevant polarization features of the target, and provides more accurate cues for restoration of surface normals. Experiments are performed using both the DeepSfP dataset and newly collected data. The results show that the proposed model can provide more accurate surface normal estimates. Compared to the UNet architecture-based method, the mean angular error is reduced by 19%, calculation time is reduced by 62%, and the model size is reduced by 11%.

In this paper, we propose a novel energy optimization framework to accurately estimate surface normal and reflectance of an object from an input image sequence. Input images are captured from a fixed viewpoint under varying lighting conditions. In the proposed approach we combine photometric stereo and Retinex constraints into our energy function. To formulate inter-image constraints, shading information is added to the Lambertian model to account for shadows. For intra-image constraints, we moderate the strength of shading smoothness according to shadow mask and normal variations. By minimizing this energy function we are able to recover accurate surface normals and reflectance. Experimental results show that our approach yields more realistic normal map and accurate albedo map than the state-of-the-art uncalibrated photometric stereo algorithms. As for intrinsic image decomposition, results on the real and synthetic scenes show that the proposed approach outperforms previous ones.

We consider the problem of estimating surface normals of a scene with spatially varying, general bidirectional reflectance distribution functions (BRDFs) observed by a static camera under varying distant illuminations. Unlike previous approaches that rely on continuous optimization of surface normals, we cast the problem as a discrete search problem over a set of finely discretized surface normals. In this setting, we show that the expensive processes can be precomputed in a scene-independent manner, resulting in accelerated inference. We discuss two variants of our discrete search photometric stereo (DSPS), one working with continuous linear combinations of BRDF bases and the other working with discrete BRDFs sampled from a BRDF space. Experiments show that DSPS has comparable accuracy to state-of-the-art exemplar-based photometric stereo methods while achieving 10-100x acceleration.

Three-dimensional reconstruction technologies are fundamental problems in computer vision. Photometric stereo recovers the surface normals of a 3D object from varying shading cues, prevailing in its capability for generating fine surface normal. In recent years, deep learning-based photometric stereo methods are capable of improving the surface-normal estimation under general non-Lambertian surfaces, due to its powerful fitting ability on the non-Lambertian surface. These state-of-the-art methods however usually regress the surface normal directly from the high-dimensional features, without exploring the embedded structural information. This results in the underutilization of the information available in the features. Therefore, in this paper, we propose an efficient manifold-based framework for learning-based photometric stereo, which can better map combined high-dimensional feature spaces to low-dimensional manifolds. Extensive experiments show that our method, learning with the low-dimensional manifolds, achieves more accurate surface-normal estimation, outperforming other state-of-the-art methods on the challenging DiLiGenT benchmark dataset.

In this paper, we propose a geometric neural network with edge-aware refinement (GeoNet++) to jointly predict both depth and surface normal maps from a single image. Building on top of two-stream CNNs, GeoNet++ captures the geometric relationships between depth and surface normals with the proposed depth-to-normal and normal-to-depth modules. In particular, the "depth-to-normal" module exploits the least square solution of estimating surface normals from depth to improve their quality, while the "normal-to-depth" module refines the depth map based on the constraints on surface normals through kernel regression. Boundary information is exploited via an edge-aware refinement module. GeoNet++ effectively predicts depth and surface normals with high 3D consistency and sharp boundaries resulting in better reconstructed 3D scenes. Note that GeoNet++ is generic and can be used in other depth/normal prediction frameworks to improve 3D reconstruction quality and pixel-wise accuracy of depth and surface normals. Furthermore, we propose a new 3D geometric metric (3DGM) for evaluating depth prediction in 3D. In contrast to current metrics that focus on evaluating pixel-wise error/accuracy, 3DGM measures whether the predicted depth can reconstruct high quality 3D surface normals. This is a more natural metric for many 3D application domains. Our experiments on NYUD-V2 [1] and KITTI [2] datasets verify that GeoNet++ produces fine boundary details and the predicted depth can be used to reconstruct high quality 3D surfaces.

This paper presents symmetric-light photometric stereo for surface normal estimation, in which directional lights are distributed symmetrically with respect to the optic center. Unlike previous studies of ring-light settings that required the information of ring radius, we show that even without the knowledge of the exact light source locations or their distances from the optic center, the symmetric configuration provides us sufficient information for recovering unique surface normals without ambiguity. Specifically, under the symmetric lights, measurements of a pair of scene points having distinct surface normals but the same albedo yield a system of constrained quadratic equations about the surface normal, which has a unique solution. Experiments demonstrate that the proposed method alleviates the need for geometric light source calibration while maintaining the accuracy of calibrated photometric stereo.

We make two contributions to the problem of shape-from-shading. First, we develop a new method for surface normal recovery. We pose the problem as that of solving the steady state heat equation subject to the hard constraint that Lambert's law is satisfied. According to this picture, the surface normals are found by taking the gradient of a scalar field. The heat equation for the scalar field can be solved using simple finite difference methods and leads to an iterative procedure for surface normal estimation. The second contribution is to show how surface height recovery from the field of surface normals can be posed as one of low dimensional embedding. We experiment with the resulting method on a variety of real-world image data, where it produces qualitatively good reconstructed surfaces.

The detection of person-borne threat objects, such as improvised explosive devices, at a safe distance is an ongoing challenge. While much attention has been given to other parts of the electromagnetic spectrum, very little is known about what potential exists to detect clothing obscured threats over the ultraviolet through the shortwave-infrared spectral region. Hyperspectral imaging may provide a greater ability to discriminate between target and non-target by using the full spectrum. This study investigates this potential by the collection and analysis of hyperspectral images of obscured proxy threat objects. The results of this study indicate a consistent ability to detect the presence of concealed objects. The study included the use of VNIR (400 nm to 1000 nm) and SWIR (1000 nm to 1700 nm), as defined here, hyperspectral imagers. Both spectral ranges provided comparable results, however, potential advantages of the SWIR spectral region are discussed.

This paper presents an empirical study to investigate the use of photometric stereo (PS) for micro-scale 3D measurement of paper samples. PS estimates per-pixel surface orientation from images of a surface captured from the same viewpoint but under different illumination directions. Specifically, we investigate the surface properties of paper to test whether they are sufficiently well approximated by a Lambertian reflectance model to allow veridical surface reconstruction under PS and explore the range of conditions for which this model is valid. We present an empirical setup that is used to conduct a series of experiments in order to analyse the applicability of PS at the micro-scale. In addition, we determine the best 4, 6, and 8 light source tilt (illumination) angles with respect to multi-source micro-scale PS. Furthermore, an intensity based image registration method is used to test the accuracy of the recovery of surface normals. The results demonstrate that at the micro-scale: (a) Lambert model represents well the data sets with low root mean square (RMS) error between the original and reconstructed image, (b) increasing the light sources from 4 to 8 reduces RMS error, and (c) PS can be used to extract veridical surface normals.

Unsupervised hyperspectral noise estimation and restoration via interband-invariant representation learning

Line-scan-based hyperspectral imaging techniques have often served as a research tool to develop rapid multispectral methods based on only a few spectral bands for rapid online applications. With continuing technological advances and greater accessibility to and availability of optoelectronic imaging sensors and spectral imaging spectrographs, the range of implementation for hyperspectral imaging has been broadening across quality and safety inspection needs in the food and agricultural industries. We have developed a series of food inspection imaging systems based on hyperspectral line-scan imaging with the use of a low-light sensitive, electron-multiplying charge-coupled device (EMCCD). In this methodology article, the spectral and spatial system performance of the latest generation of the ARS hyperspectral imaging system, which is capable of reflectance and fluorescence measurements in the visible and near-infrared (NIR) spectral regions from 400 to 1000 nm, is evaluated. Results show that the spectral resolution of the system is 4.4 nm at full-width at half-maximum (FWHM) and 6 nm FWHM at our typical operation mode (6-pixel spectral binning). We enhanced the system throughput responses by using spectral weighting filters to better utilize the dynamic range of the analog-to-digital converter. With this system throughput adjustment, noise-equivalent reflectance measurements were significantly reduced by approximately 50% in the NIR region for a range of standard diffuse reflectance targets. The responsivity of the system from 450 to 950 nm was determined to be linear.

This paper presents a novel method for 3D surface reconstruction that uses polarization and shading information from two views. The method relies on polarization data acquired using a standard digital camera and a linear polarizer. Fresnel theory is used to process the raw images and to obtain initial estimates of surface normals, assuming that the reflection type is diffuse. Based on this idea, the paper presents two novel contributions to the problem of surface reconstruction. The first is a technique to enhance the surface normal estimates by incorporating shading information into the method. This is done using robust statistics to estimate how the measured pixel brightnesses depend on the surface orientation. This gives an estimate of the object material reflectance function, which is used to refine the estimates of the surface normals. The second contribution is to use the refined estimates to establish correspondence between two views of an object. To do this, a set of patches are extracted from each view and are aligned by minimizing an energy functional based on the surface normal estimates and local topographic properties. The optimum alignment parameters for different patch pairs are then used to establish stereo correspondence. This process results in an unambiguous field of surface normals, which can be integrated to recover the surface depth. Our technique is most suited to smooth, non-metallic surfaces. It complements existing stereo algorithms since it does not require salient surface features to obtain correspondences. An extensive set of experiments, yielding reconstructed objects and reflectance functions, are presented and compared to ground truth.

Detection of fish fillet substitution and mislabeling using multimode hyperspectral imaging techniques