Color Subspaces as Photometric Invariants

DRM-Based Colour Photometric Stereo Using Diffuse-Specular Separation for Non-Lambertian Surfaces

This paper presents a photometric stereo (PS) method based on the dichromatic reflectance model (DRM) using colour images. The proposed method estimates surface orientations for surfaces with non-Lambertian reflectance using diffuse-specular separation and contains two steps. The first step, referred to as diffuse-specular separation, initialises surface orientations in a specular invariant colour subspace and further separates the diffuse and specular components in the RGB space. In the second step, the surface orientations are refined by first initialising specular parameters via solving a log-linear regression problem owing to the separation and then fitting the DRM using Levenburg-Marquardt algorithm. Since reliable information from diffuse reflection free from specularities is adopted in the initialisations, the proposed method is robust and feasible with less observations. At pixels where dense non-Lambertian reflectances appear, signals from specularities are exploited to refine the surface orientations and the additionally acquired specular parameters are potentially valuable for more applications, such as digital relighting. The effectiveness of the newly proposed surface normal refinement step was evaluated and the accuracy in estimating surface orientations was enhanced around 30% on average by including this step. The proposed method was also proven effective in an experiment using synthetic input images comprised of twenty-four different reflectances of dielectric materals. A comparison with nine other PS methods on five representative datasets further prove the validity of the proposed method.

Performance of a Deep Neural Network Algorithm Based on a Small Medical Image Dataset: Incremental Impact of 3D-to-2D Reformation Combined with Novel Data Augmentation, Photometric Conversion, or Transfer Learning

Collecting and curating large medical-image datasets for deep neural network (DNN) algorithm development is typically difficult and resource-intensive. While transfer learning (TL) decreases reliance on large data collections, current TL implementations are tailored to two-dimensional (2D) datasets, limiting applicability to volumetric imaging (e.g., computed tomography). Targeting performance enhancement of a DNN algorithm based on a small image dataset, we assessed incremental impact of 3D-to-2D projection methods, one supporting novel data augmentation (DA); photometric grayscale-to-color conversion (GCC); and/or TL on training of an algorithm from a small coronary computed tomography angiography (CCTA) dataset (200 examinations, 50% with atherosclerosis and 50% atherosclerosis-free) producing 245 diseased and 1127 normal coronary arteries/branches. Volumetric CCTA data was converted to a 2D format creating both an Aggregate Projection View (APV) and a Mosaic Projection View (MPV), supporting DA per vessel; both grayscale and color-mapped versions of each view were also obtained. Training was performed both without and with TL, and algorithm performance of all permutations was compared using area under the receiver operating characteristics curve. Without TL, APV performance was 0.74 and 0.87 on grayscale and color images, respectively, compared to 0.90 and 0.87 for MPV. With TL, APV performance was 0.78 and 0.88 on grayscale and color images, respectively, compared with 0.93 and 0.91 for MPV. In conclusion, TL enhances performance of a DNN algorithm from a small volumetric dataset after proposed 3D-to-2D reformatting, but additive gain is achieved with application of either GCC to APV or the proposed novel MPV technique for DA.

A Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo

Classic photometric stereo is often extended to deal with real-world materials and work with unknown lighting conditions for practicability. To quantitatively evaluate non-Lambertian and uncalibrated photometric stereo, a photometric stereo image dataset containing objects of various shapes with complex reflectance properties and high-quality ground truth normals is still missing. In this paper, we introduce the 'DiLiGenT' dataset with calibrated Directional Lightings, objects of General reflectance with different shininess, and 'ground Truth' normals from high-precision laser scanning. We use our dataset to quantitatively evaluate state-of-the-art photometric stereo methods for general materials and unknown lighting conditions, selected from a newly proposed photometric stereo taxonomy emphasizing non-Lambertian and uncalibrated methods. The dataset and evaluation results are made publicly available, and we hope it can serve as a benchmark platform that inspires future research.

Illumination estimation from specular highlight in a multi-spectral image

The reflection spectrum of an object characterizes its surface material, but for non-Lambertian scenes, the recorded spectrum often deviates owing to specular contamination. To compensate for this deviation, the illumination spectrum is required, and it can be estimated from specularity. However, existing illumination-estimation methods often degenerate in challenging cases, especially when only weak specularity exists. By adopting the dichromatic reflection model, which formulates a specular-influenced image as a linear combination of diffuse and specular components, this paper explores two individual priors and one mutual prior upon these two components: (i) The chromaticity of a specular component is identical over all the pixels. (ii) The diffuse component of a specular-contaminated pixel can be reconstructed using its specular-free counterpart describing the same material. (iii) The spectrum of illumination usually has low correlation with that of diffuse reflection. A general optimization framework is proposed to estimate the illumination spectrum from the specular component robustly and accurately. The results of both simulation and real experiments demonstrate the robustness and accuracy of our method.

Segmentation and estimation of spatially varying illumination

In this paper, we present an unsupervised method for segmenting the illuminant regions and estimating the illumination power spectrum from a single image of a scene lit by multiple light sources. Here, illuminant region segmentation is cast as a probabilistic clustering problem in the image spectral radiance space. We formulate the problem in an optimization setting, which aims to maximize the likelihood of the image radiance with respect to a mixture model while enforcing a spatial smoothness constraint on the illuminant spectrum. We initialize the sample pixel set under each illuminant via a projection of the image radiance spectra onto a low-dimensional subspace spanned by a randomly chosen subset of spectra. Subsequently, we optimize the objective function in a coordinate-ascent manner by updating the weights of the mixture components, sample pixel set under each illuminant, and illuminant posterior probabilities. We then estimate the illuminant power spectrum per pixel making use of these posterior probabilities. We compare our method with a number of alternatives for the tasks of illumination region segmentation, illumination color estimation, and color correction. Our experiments show the effectiveness of our method as applied to one hyperspectral and three trichromatic image data sets.

Illuminant direction estimation for a single image based on local region complexity analysis and average gray value

Illuminant direction estimation is an important research issue in the field of image processing. Due to low cost for getting texture information from a single image, it is worthwhile to estimate illuminant direction by employing scenario texture information. This paper proposes a novel computation method to estimate illuminant direction on both color outdoor images and the extended Yale face database B. In our paper, the luminance component is separated from the resized YCbCr image and its edges are detected with the Canny edge detector. Then, we divide the binary edge image into 16 local regions and calculate the edge level percentage in each of them. Afterward, we use the edge level percentage to analyze the complexity of each local region included in the luminance component. Finally, according to the error function between the measured intensity and the calculated intensity, and the constraint function for an infinite light source model, we calculate the illuminant directions of the luminance component's three local regions, which meet the requirements of lower complexity and larger average gray value, and synthesize them as the final illuminant direction. Unlike previous works, the proposed method requires neither all of the information of the image nor the texture that is included in the training set. Experimental results show that the proposed method works better at the correct rate and execution time than the existing ones.

Inverse rendering of faces with a 3D morphable model

In this paper, we present a complete framework to inverse render faces with a 3D Morphable Model (3DMM). By decomposing the image formation process into geometric and photometric parts, we are able to state the problem as a multilinear system which can be solved accurately and efficiently. As we treat each contribution as independent, the objective function is convex in the parameters and a global solution is guaranteed. We start by recovering 3D shape using a novel algorithm which incorporates generalization error of the model obtained from empirical measurements. We then describe two methods to recover facial texture, diffuse lighting, specular reflectance, and camera properties from a single image. The methods make increasingly weak assumptions and can be solved in a linear fashion. We evaluate our findings on a publicly available database, where we are able to outperform an existing state-of-the-art algorithm. We demonstrate the usability of the recovered parameters in a recognition experiment conducted on the CMU-PIE database.

Biologically inspired framework for spatial and spectral velocity estimations

The multichannel gradient model (McGM) is an established, biologically plausible framework for the robust extraction of image velocity. Here we describe the McGM extension into color space and report the resulting performance improvement. Our new model, in contrast to existing approaches that process color channels separately, incorporates spectral energy measures to form a local description of the stimulus chromatic spatio-temporal structure from which we can recover both spatial and spectral velocities. We present a range of comparative experiments on synthetic and natural test data that demonstrate that our new method reduces errors and is more robust over a range of viewing environments.

Robust stereo matching using adaptive normalized cross-correlation

A majority of the existing stereo matching algorithms assume that the corresponding color values are similar to each other. However, it is not so in practice as image color values are often affected by various radiometric factors such as illumination direction, illuminant color, and imaging device changes. For this reason, the raw color recorded by a camera should not be relied on completely, and the assumption of color consistency does not hold good between stereo images in real scenes. Therefore, the performance of most conventional stereo matching algorithms can be severely degraded under the radiometric variations. In this paper, we present a new stereo matching measure that is insensitive to radiometric variations between left and right images. Unlike most stereo matching measures, we use the color formation model explicitly in our framework and propose a new measure, called the Adaptive Normalized Cross-Correlation (ANCC), for a robust and accurate correspondence measure. The advantage of our method is that it is robust to lighting geometry, illuminant color, and camera parameter changes between left and right images, and does not suffer from the fattening effect unlike conventional Normalized Cross-Correlation (NCC). Experimental results show that our method outperforms other state-of-the-art stereo methods under severely different radiometric conditions between stereo images.