Traditional analytical reflectance models, while compact and interpretable, lack the capacity to accurately represent physical measurements. Recent neural models, which closely fit input data, are less generalizable and often more expensive to store and evaluate. To combine the strengths and overcome the limitations of these two classes of models, we present neural enhancement, a novel framework to boost an input analytical appearance model, by identifying and replacing its key computational nodes/operators with small-scale multi-layer perceptrons. This allows us to leverage the computational graph structure of the original model, while improving its expressiveness at a modest cost. To make the enhancement computationally tractable, we propose a hypercube-based search to automatically and efficiently identify the node(s) and/or operator(s) to be replaced towards maximal gain in a differentiable fashion. We enhance a number of common analytical BRDF models. The results are, at once accurate, compact and efficient, and compare favorably with state-of-the-art work on fitting measured reflectance. Finally, our models are fully compatible with standard rasterization or ray-tracing pipeline.

High-quality material generation is key for virtual environment authoring and inverse rendering. We propose MaterialPicker, a multi-modal material generator leveraging a Diffusion Transformer (DiT) architecture, improving and simplifying the creation of high-quality materials from text prompts and/or photographs. Our method can generate a material based on an image crop of a material sample, even if the captured surface is distorted, viewed at an angle or partially occluded, as is often the case in photographs of natural scenes. We further allow the user to specify a text prompt to provide additional guidance for the generation. We finetune a pre-trained DiT-based video generator into a material generator, where each material map is treated as a frame in a video sequence. We evaluate our approach both quantitatively and qualitatively and show that it enables more diverse material generation and better distortion correction than previous work.

We present a novel framework to efficiently acquire anisotropic reflectance in a pixel-independent fashion, using a deep gated mixture-of-experts. While existing work employs a unified network to handle all possible input, our network automatically learns to condition on the input for enhanced reconstruction. We train a gating module that takes photometric measurements as input and selects one out of a number of specialized decoders for reflectance reconstruction, essentially trading generality for quality. A common pre-trained latent-transform module is also appended to each decoder, to offset the burden of the increased number of decoders. In addition, the illumination conditions during acquisition can be jointly optimized. The effectiveness of our framework is validated on a wide variety of challenging near-planar samples with a lightstage. Compared with the state-of-the-art technique, our quality is improved with the same number of input images, and our input image number can be reduced to about 1/3 for equal-quality results. We further generalize the framework to enhance a state-of-the-art technique on non-planar reflectance scanning.

We present the first large-scale database of measured spatially-varying anisotropic reflectance, consisting of 1,000 high-quality near-planar SVBRDFs, spanning 9 material categories such as wood, fabric and metal. Each sample is captured in 15 minutes, and represented as a set of high-resolution texture maps that correspond to spatially-varying BRDF parameters and local frames. To build this database, we develop a novel integrated system for robust, high-quality and -efficiency reflectance acquisition and reconstruction. Our setup consists of 2 cameras and 16,384 LEDs. We train 64 lighting patterns for efficient acquisition, in conjunction with a network that predicts per-point reflectance in a neural representation from carefully aligned two-view measurements captured under the patterns. The intermediate results are further fine-tuned with respect to the photographs acquired under 63 effective linear lights, and finally fitted to a BRDF model. We report various statistics of the database, and demonstrate its value in the applications of material generation, classification as well as sampling. All related data, including future additions to the database, can be downloaded from https://opensvbrdf.github.io/.

We present a novel framework to learn to convert the per-pixel photometric information at each view into spatially distinctive and view-invariant low-level features, which can be plugged into existing multi-view stereo pipeline for enhanced 3D reconstruction. Both the illumination conditions during acquisition and the subsequent per-pixel feature transform can be jointly optimized in a differentiable fashion. Our framework automatically adapts to and makes efficient use of the geometric information available in different forms of input data. High-quality 3D reconstructions of a variety of challenging objects are demonstrated on the data captured with an illumination multiplexing device, as well as a point light. Our results compare favorably with state-of-the-art techniques.

We propose neural trace photography, a novel framework to automatically learn high-quality scanning of non-planar, complex anisotropic appearance. Our key insight is that free-form appearance scanning can be cast as a geometry learning problem on unstructured point clouds, each of which represents an image measurement and the corresponding acquisition condition. Based on this connection, we carefully design a neural network, to jointly optimize the lighting conditions to be used in acquisition, as well as the spatially independent reconstruction of reflectance from corresponding measurements. Our framework is not tied to a specific setup, and can adapt to various factors in a data-driven manner. We demonstrate the effectiveness of our framework on a number of physical objects with a wide variation in appearance. The objects are captured with a light-weight mobile device, consisting of a single camera and an RGB LED array. We also generalize the framework to other common types of light sources, including a point, a linear and an area light.

In the era of Industrial Internet of Things (IIoT), huge amounts of data are generated, and companies are highly motivated to store the data on cloud servers for cost saving and efficient application. However, the IIoT data are always of great value. The direct outsourcing of such data can leak the important information of the companies and cause great business losses. A straightforward solution is to encrypt the data by using standard encryption methods before outsourcing. Nevertheless, this will make data utilization quite inconvenient. This paper focuses on the secure process of image data on cloud servers. Images are stored on cloud servers in encrypted form, and the local binary pattern feature can be directly extracted from the encrypted images for applications. The security analysis and experimental results demonstrate the security and effectiveness of our scheme.

The Flux Switching Machine is one of the novel topologies within the hybrid machine class. It has many advantages such as flux focusing effect, compatibility with simple power converters, high fault tolerance with independent concentrated armature windings, mechanical robustness due to its simple salient pole rotor and high power density. With such attributes the machine is a promising candidate for high speed, high power density applications. It includes toothed rotor with permanent magnet excitation and segmented rotor with field coil excitation. This article reports on comparative studies into the mechanical stress, magnetic flux, back EMF, D axis, Q axis inductance and saliency ratio, loss distribution, efficiency and power density for these topologies via finite element analysis under open circuit and various load conditions. Quantitative simulation results reveal that the segmented rotor with field coil excitation topologies exhibit better electromagnetic performance, among which the 12/7 combination of stator pole and rotor segments exhibits superior EM performances than those of other combinations. Parametric analysis with respect to the aspect ratio and rotor segment arc angle are also performed on 12/7 topology to investigate their relationship with the torque, efficiency and power density.

A novel control method using H∞tracking and integral reinforcement learning is applied to a flux-switching permanent magnet (FSPM) machine in a hostile environment. The proposed controller can maintain high performance in the presence of motor parameter uncertainties and load disturbances. The conventional design procedure for an H∞controller is to solve the Hamilton-Jacobi-Isaacs (HJI) equation which requires full information of the system model. The novel control method, the integral reinforcement learning (IRL) makes use of neural networks to parametrically represent the control policy and the performance of system, and learns the solution of HJI equations online. Therefore, the FSPM machine can work optimally under parameter uncertainties due to different operating conditions. The simulation in Matlab/Simulink vividly illustrates the control performance for a 45kW, rotor speed 9000 rpm, 12/5 poles flux-switching permanent magnet machine.