Search

Measuring 3D geometric structures of indoor scenes requires dedicated depth sensors, which are not always available. Echo-based depth estimation has recently been studied as a promising alternative solution. All previous studies have assumed the use of echoes in the audible range. However, one major problem is that audible echoes cannot be used in quiet spaces or other situations where producing audible sounds is prohibited. In this paper, we consider echo-based depth estimation using inaudible ultrasonic echoes. While ultrasonic waves provide high measurement accuracy in theory, the actual depth estimation accuracy when ultrasonic echoes are used has remained unclear, due to its disadvantage of being sensitive to noise and susceptible to attenuation. We first investigate the depth estimation accuracy when the frequency of the sound source is restricted to the high-frequency band, and found that the accuracy decreased when the frequency was limited to ultrasonic ranges. Based on this observation, we propose a novel deep learning method to improve the accuracy of ultrasonic echo-based depth estimation by using audible echoes as auxiliary data only during training. Experimental results with a public dataset demonstrate that our method improves the estimation accuracy., Comment: ICIP 2024

Galaxies that cause the strong gravitational lensing of background galaxies provide us crucial information about the distribution of matter around them. Traditional modelling methods that analyse such strong lenses are both time and resource consuming, require sophisticated lensing codes and modelling expertise. To study the large lens population expected from imaging surveys such as LSST, we need fast and automated analysis methods. In this work, we build and train a simple convolutional neural network with an aim to rapidly predict model parameters of gravitational lenses. We focus on the most important lens mass model parameters, namely, the Einstein radius, the axis ratio and the position angle of the major axis of the mass distribution. The network is trained on a variety of simulated data with an increasing degree of realism and shows satisfactory performance on simulated test data. The trained network is then applied to the real sample of galaxy-scale candidate lenses from the Subaru HSC, a precursor survey to LSST. Unlike the simulated lenses, we do not have the ground truth for the real lenses. Therefore, we have compared our predictions with those from YattaLens, a lens modelling pipeline. Additionally, we also compare the parameter predictions for 10 HSC lenses that were also studied by other conventional modelling methods. These comparisons show a fair quantitative agreement on the Einstein radius, although the axis ratio and the position angle from the network as well as the individual modelling methods, seem to have systematic uncertainties beyond the quoted errors., Comment: 10 pages, 9 figures

Unsupervised intrinsic image decomposition (IID) is the process of separating a natural image into albedo and shade without these ground truths. A recent model employing light detection and ranging (LiDAR) intensity demonstrated impressive performance, though the necessity of LiDAR intensity during inference restricts its practicality. Thus, IID models employing only a single image during inference while keeping as high IID quality as the one with an image plus LiDAR intensity are highly desired. To address this challenge, we propose a novel approach that utilizes only an image during inference while utilizing an image and LiDAR intensity during training. Specifically, we introduce a partially-shared model that accepts an image and LiDAR intensity individually using a different specific encoder but processes them together in specific components to learn shared representations. In addition, to enhance IID quality, we propose albedo-alignment loss and image-LiDAR conversion (ILC) paths. Albedo-alignment loss aligns the gray-scale albedo from an image to that inferred from LiDAR intensity, thereby reducing cast shadows in albedo from an image due to the absence of cast shadows in LiDAR intensity. Furthermore, to translate the input image into albedo and shade style while keeping the image contents, the input image is separated into style code and content code by encoders. The ILC path mutually translates the image and LiDAR intensity, which share content but differ in style, contributing to the distinct differentiation of style from content. Consequently, LIET achieves comparable IID quality to the existing model with LiDAR intensity, while utilizing only an image without LiDAR intensity during inference.