This study introduces a novel method to mitigate temporal illumination variations in whisk-broom hyperspectral imaging under varying environmental illumination conditions. Whisk-broom hyperspectral imaging captures high resolution spectra pixel-by-pixel sequentially, a process susceptible to sunlight fluctuations over time, particularly when imaging cultural artifacts outdoors. Despite sunlight's broad spectrum, its variability over time can compromise the quality of hyperspectral images, affecting data analysis. Prior strategies suggested a supplementary single compensating vertical scan alongside the standard row-wise raster scan. However, this strategy fails when the additional single vertical scan is performed near or on a black frame. Building on this, our study proposes using two scans, one performed orthogonally to the traditional row-wise scan, to counteract illumination variations. Furthermore, we formulate the compensation problem in logarithmic space, exploiting the low-dimensional structure of the reflectance and illumination spectra. Using total variation penalization in the cost function enhances smoothness. Our method achieves robust compensation for changes in environmental illumination. We also demonstrate that we can use multiple columns from the column-wise scan without significantly decreasing the compensation quality while reducing acquisition time. We illustrate the application of our methods to hyperspectral images of stained-glass windows of the historic Cathedrale Notre-Dame d'Amiens in France.

We propose a novel method for estimating head orientation from a low-resolution far-infrared (LFIR) image sequence captured by a 32 × 32 FIR sensor array. Estimating head orientation from LFIR images is challenging due to their inherent noise and limited resolution. Manually an-notating head orientation is also difficult, and no suitable dataset currently exists. We propose the LFIR2Head model, which leverages a multimodal-temporal framework for robust estimation. We also introduce the LFIR2Head dataset, which was created using an automatic annotation system. Extensive experiments demonstrate the accuracy of head orientation estimation with the proposed dataset. We con-firmed that head orientation can be estimated accurately from an LFIR image sequence.

Abstract We propose deep depth from focal stack (DDFS), which takes a focal stack as input of a neural network for estimating scene depth. Defocus blur is a useful cue for depth estimation. However, the size of the blur depends on not only scene depth but also camera settings such as focus distance, focal length, and f-number. Current learning-based methods without any defocus models cannot estimate a correct depth map if camera settings are different at training and test times. Our method takes a plane sweep volume as input for the constraint between scene depth, defocus images, and camera settings, and this intermediate representation enables depth estimation with different camera settings at training and test times. This camera-setting invariance can enhance the applicability of DDFS. The experimental results also indicate that our method is robust against a synthetic-to-real domain gap.

Non-line-of-sight (NLOS) imaging is conducted to infer invisible scenes from indirect light on visible objects. The neural transient field (NeTF) was proposed for representing scenes as neural radiance fields in NLOS scenes. We propose NLOS neural implicit surface (NLOS-NeuS), which extends the NeTF to neural implicit surfaces with a signed distance function (SDF) for reconstructing three-dimensional surfaces in NLOS scenes. We introduce two constraints as loss functions for correctly learning an SDF to avoid non-zero level-set surfaces. We also introduce a lower bound constraint of an SDF based on the geometry of the first-returning photons. The experimental results indicate that these constraints are essential for learning a correct SDF in NLOS scenes. Compared with previous methods with discretized representation, NLOS-NeuS with the neural continuous representation enables us to reconstruct smooth surfaces while preserving fine details in NLOS scenes. To the best of our knowledge, this is the first study on neural implicit surfaces with volume rendering in NLOS scenes. Project page: https://yfujimura.github.io/nlos-neus/

A parasitic egg could cause infections and become significant diseases, especially in countries with poor sanitation and hygiene. Its detection which is manually conducted by humans using a microscope could be time-consuming and potent to misclassify. The goal of this research is to get a method that has a good accuracy to automatically detect and identify the parasitic egg. Also, we have a challenge here because the dataset has different resolutions, lighting, and setting conditions. Here we try to utilize the YOLO algorithm by doing image augmentation and restoration to the dataset, we use deep latent space translation for restoration and a simple GrabCut algorithm to generate an augmented image. Furthermore, we apply hyperparameter tuning in image resolution and see how we could utilize the YOLO algorithm to do fast and accurate classification. From the result, we get the combination could give better results in classifying the parasitic egg which the mIoU results reached 71.7 percent.

We propose a learning-based multi-view stereo (MVS) method in scattering media, such as fog or smoke, with a novel cost volume, called the dehazing cost volume. Images captured in scattering media are degraded due to light scattering and attenuation caused by suspended particles. This degradation depends on scene depth; thus, it is difficult for traditional MVS methods to evaluate photometric consistency because the depth is unknown before three-dimensional (3D) reconstruction. The dehazing cost volume can solve this chicken-and-egg problem of depth estimation and image restoration by computing the scattering effect using swept planes in the cost volume. We also propose a method of estimating scattering parameters, such as airlight, and a scattering coefficient, which are required for our dehazing cost volume. The output depth of a network with our dehazing cost volume can be regarded as a function of these parameters; thus, they are geometrically optimized with a sparse 3D point cloud obtained at a structure-from-motion step. Experimental results on synthesized hazy images indicate the effectiveness of our dehazing cost volume against the ordinary cost volume regarding scattering media. We also demonstrated the applicability of our dehazing cost volume to real foggy scenes.

Images captured in participating media such as murky water, fog, or smoke are degraded by scattered light. Thus, the use of traditional three-dimensional (3D) reconstruction techniques in such environments is difficult. In this paper, we propose a photometric stereo method for participating media. The proposed method differs from prvious studies with respect to modeling shape-dependent forward scatter. In the proposed model, forward scatter is described as an analytical form using lookup tables and is represented by spatially-variant kernels. We also propose an approximation of a large-scale dense matrix as a sparse matrix, which enables the removal of forward scatter. We discuss the approximation in the proposed method using synthesized data. Then, experiments with real data demonstrate that the proposed method improves 3D reconstruction in participating media.

Images captured in participating media such as murky water, fog, or smoke are degraded by scattered light. Thus, the use of traditional three-dimensional (3D) reconstruction techniques in such environments is difficult. In this paper, we propose a photometric stereo method for participating media. The proposed method differs from previous studies with respect to modeling shape-dependent forward scatter. In the proposed model, forward scatter is described as an analytical form using lookup tables and is represented by spatially-variant kernels. We also propose an approximation of a large-scale dense matrix as a sparse matrix, which enables the removal of forward scatter. Experiments with real and synthesized data demonstrate that the proposed method improves 3D reconstruction in participating media.