Search

Airbnb is a platform company that provides and directs connections between hosts and guests. People who have an open room or a vacant space can become a host on Airbnb and make it available to the world community. Airbnb offers hosts an easy way to turn otherwise wasted space into profitable space. Therefore, it is particularly necessary for hosts to forecast and analyze the price of the houses they own. Machine learning is the science of developing algorithms and statistical models. The regression model is a predictive modeling technique in machine learning. This technique is often used to discover causal relationships between variables, predictive analysis, and time series models. In this project, our goal is to predict Boston Airbnb listing prices through a variety of machine-learning methods. This paper chose four regression models, which are the random forest regression model, linear regression model, K-nearest neighbor regression model, and Gradient Boosting regression model. With one of the best regression models, this paper obtained R-squared values of 0.6593 in training and 0.7198 in testing on the Boston dataset.

A fundamental challenge in fluorescence microscopy is the photon shot noise arising from the inevitable stochasticity of photon detection. Noise increases measurement uncertainty and limits imaging resolution, speed and sensitivity. To achieve high-sensitivity fluorescence imaging beyond the shot-noise limit, we present DeepCAD-RT, a self-supervised deep learning method for real-time noise suppression. Based on our previous framework DeepCAD, we reduced the number of network parameters by 94%, memory consumption by 27-fold and processing time by a factor of 20, allowing real-time processing on a two-photon microscope. A high imaging signal-to-noise ratio can be acquired with tenfold fewer photons than in standard imaging approaches. We demonstrate the utility of DeepCAD-RT in a series of photon-limited experiments, including in vivo calcium imaging of mice, zebrafish larva and fruit flies, recording of three-dimensional (3D) migration of neutrophils after acute brain injury and imaging of 3D dynamics of cortical ATP release. DeepCAD-RT will facilitate the morphological and functional interrogation of biological dynamics with a minimal photon budget.

Undercarriage device is one of the essential parts of an aeroplane, and accurate detection of whether the aeroplane undercarriage is operating normally can effectively avoid aeroplane accidents. To address the problems of low automation and low accuracy of small target detection in existing aeroplane undercarriage detection methods, an improved algorithm for aeroplane undercarriage detection YOLO V4 is proposed. Firstly, the convolutional network structure of Inception-ResNet is integrated into the CSPDarkNet53 framework to improve the algorithm’s ability to extract semantic information of target features; then an attention mechanism is added to the path aggregation network algorithm structure to improve the importance and relevance of different features after conceptual operations. In addition, aeroplane and undercarriage datasets were constructed, and finally, the generated partitioned test sets were tested to evaluate the test performance of Faster R-CNN, YOLO V3, and YOLO V4 target detection algorithms. The experimental results show that the improved algorithm has significantly improved the recall rate and the mean accuracy of detection for small targets in our dataset compared with the YOLO V4 algorithm. The reasonableness and advancedness of the improved algorithm in this paper are effectively verified.

As an essential step in the pathological diagnosis, histochemical staining can show specific tissue structure information and, consequently, assist pathologists in making accurate diagnoses. Clinical kidney histopathological analyses usually employ more than one type of staining: H&E, MAS, PAS, PASM, etc. However, due to the interference of colors among multiple stains, it is not easy to perform multiple staining simultaneously on one biological tissue. To address this problem, we propose a network based on unpaired training data to virtually generate multiple types of staining from one staining. Our method can preserve the content of input images while transferring them to multiple target styles accurately. To efficiently control the direction of stain transfer, we propose a style guided normalization (SGN). Furthermore, a multiple style encoding (MSE) is devised to represent the relationship among different staining styles dynamically. An improved one-hot label is also proposed to enhance the generalization ability and extendibility of our method. Vast experiments have demonstrated that our model can achieve superior performance on a tiny dataset. The results exhibit not only good performance but also great visualization and interpretability. Especially, our method also achieves satisfactory results over cross-tissue, cross-staining as well as cross-task. We believe that our method will significantly influence clinical stain transfer and reduce the workload greatly for pathologists. Our code and Supplementary materials are available at https://github.com/linyiyang98/UMDST.

High-quality magnetic resonance (MR) images afford more detailed information for reliable diagnoses and quantitative image analyses. Given low-resolution (LR) images, the deep convolutional neural network (CNN) has shown its promising ability for image super-resolution (SR). The LR MR images usually share some visual characteristics: structural textures of different sizes, edges with high correlation, and less informative background. However, multi-scale structural features are informative for image reconstruction, while the background is more smooth. Most previous CNN-based SR methods use a single receptive field and equally treat the spatial pixels (including the background). It neglects to sense the entire space and get diversified features from the input, which is critical for high-quality MR image SR. We propose a wide weighted attention multi-scale network (W2AMSN) for accurate MR image SR to address these problems. On the one hand, the features of varying sizes can be extracted by the wide multi-scale branches. On the other hand, we design a non-reduction attention mechanism to recalibrate feature responses adaptively. Such attention preserves continuous cross-channel interaction and focuses on more informative regions. Meanwhile, the learnable weighted factors fuse extracted features selectively. The encapsulated wide weighted attention multi-scale block (W2AMSB) is integrated through a recurrent framework and global attention mechanism. Extensive experiments and diversified ablation studies show the effectiveness of our proposed W2AMSN, which surpasses state-of-the-art methods on most popular MR image SR benchmarks quantitatively and qualitatively. And our method still offers superior accuracy and adaptability on real MR images.

Deep learning based algorithms have been widely employed to build reliable steel surface defect detection systems, which are important for manufacturing. The performance of deep learning models relies heavily on abundant annotated data. Nevertheless, the labeled image volume in industrial datasets is often limited. The scarcity of training data would lead to poor detection precision. To tackle this issue, we propose the first few-shot defect detection framework. Through pre-training models using data relevant to the target task, the proposed framework can produce well-trained networks with a few labeled images. Meanwhile, we release the first publicly available few-shot defect detection dataset, namely few-shot NEU-DET (FS-ND). This dataset will serve as a fair benchmark for contrasting various methods. Afterwards, we analyze the characteristics of steel surface defect detection. It is observed that the limited amount of training data can hardly cover the data distributions in practical applications. Given this observation, we develop two domain generalization strategies that enhance the appearance and scale diversity of extracted features. Furthermore, it is found that noise existing in industrial images could result in the collapse of models. To address this problem, we devise a noise regularization strategy that improves the robustness of trained models significantly. We have conducted extensive experiments to evaluate the effectiveness of our framework. The results indicate that our framework outperforms the contrasted baseline by around 15 mAP and achieves comparable performance with models trained using abundant data.

Photosystem II repair in chloroplasts is a critical process involved in maintaining a plant’s photosynthetic activity under cold stress. FtsH (filamentation temperature-sensitive H) is an essential metalloprotease that is required for chloroplast photosystem II repair. However, the role of FtsH in tea plants and its regulatory mechanism under cold stress remains elusive. In this study, we cloned a FtsH homolog gene in tea plants, named CsFtsH5, and found that CsFtsH5 was located in the chloroplast and cytomembrane. RT-qPCR showed that the expression of CsFtsH5 was increased with leaf maturity and was significantly induced by light and cold stress. Transient knockdown CsFtsH5 expression in tea leaves using antisense oligonucleotides resulted in hypersensitivity to cold stress, along with higher relative electrolyte leakage and lower Fv/Fm values. To investigate the molecular mechanism underlying CsFtsH5 involvement in the cold stress, we focused on the calcineurin B-like-interacting protein kinase 11 (CsCIPK11), which had a tissue expression pattern similar to that of CsFtsH5 and was also upregulated by light and cold stress. Yeast two-hybrid and dual luciferase (Luc) complementation assays revealed that CsFtsH5 interacted with CsCIPK11. Furthermore, the Dual-Luc assay showed that CsCIPK11-CsFtsH5 interaction might enhance CsFtsH5 stability. Altogether, our study demonstrates that CsFtsH5 is associated with CsCIPK11 and plays a positive role in maintaining the photosynthetic activity of tea plants in response to low temperatures.

Kresling pattern origami-inspired structural design has been widely investigated using its bistable property and the single coupling degree of freedom (DOF). In order to obtain new properties or new origami-inspired structures, it needs to innovate the crease lines in the flat sheet of Kresling pattern origami. Here, we present a derivative of Kresling pattern origami—multi-triangles cylindrical origami (MTCO) with tristable property. The truss model is modified based on the switchable active crease lines during the folding motion of the MTCO. Using the energy landscape obtained from the modified truss model, the tristable property is validated and extended to Kresling pattern origami. Simultaneously, the high stiffness property of the third stable state and some special stable states are discussed. In addition, MTCO-inspired metamaterials with deployable property and tunable stiffness, and MTCO-inspired robotic arms with wide movement ranges and rich motion forms are created. These works promote research on Kresling pattern origami, and the design ideas of the metamaterials and robotic arms play a positive role in improving the stiffness of deployable structures and conceiving motion robots.

Few-shot semantic segmentation aims to learn to segment unseen class objects with the guidance of only a few support images. Most previous methods rely on the pixel-level label of support images. In this paper, we focus on a more challenging setting, in which only the image-level labels are available. We propose a general framework to firstly generate coarse masks with the help of the powerful vision-language model CLIP, and then iteratively and mutually refine the mask predictions of support and query images. Extensive experiments on PASCAL-5i and COCO-20i datasets demonstrate that our method not only outperforms the state-of-the-art weakly supervised approaches by a significant margin, but also achieves comparable or better results to recent supervised methods. Moreover, our method owns an excellent generalization ability for the images in the wild and uncommon classes. Code will be available at https://github.com/Whileherham/IMR-HSNet., ijcai 2022

This work was aimed to elucidate the mechanism of action of Han-Shi-Yu-Fei-decoction (HSYFD) for treating patients with mild coronavirus disease 2019 (COVID-19) based on clinical symptom-guided network pharmacology. Experimentally, an ultra-high performance liquid chromatography technique coupled with quadrupole time-of-flight mass spectrometry method was used to profile the chemical components and the absorbed prototype constituents in rat serum after its oral administration, and 11 out of 108 compounds were identified. Calculatingly, the disease targets of Han-Shi-Yu-Fei symptoms of COVID-19 were constructed through the TCMIP V2.0 database. The subsequent network pharmacology and molecular docking analysis explored the molecular mechanism of the absorbed prototype constituents in the treatment of COVID-19. A total of 42 HSYFD targets oriented by COVID-19 clinical symptom were obtained, with EGFR, TP53, TNF, JAK2, NR3C1, TH, COMT, and DRD2 as the core targets. Enriched pathway analysis yielded multiple COVID-19-related signaling pathways, such as the PI3K/AKT signaling pathway and JAK-STAT pathway. Molecular docking showed that the key compounds, such as 6-gingerol, 10-gingerol, and scopoletin, had high binding activity to the core targets like COMT, JAK2, and NR3C1. Our work also verified the feasibility of clinical symptom-guided network pharmacology analysis of chemical compounds, and provided a possible agreement between the points of views of traditional Chinese medicine and western medicine on the disease.

Hyperspectral image (HSI) reconstruction aims to recover the 3D spatial-spectral signal from a 2D measurement in the coded aperture snapshot spectral imaging (CASSI) system. The HSI representations are highly similar and correlated across the spectral dimension. Modeling the inter-spectra interactions is beneficial for HSI reconstruction. However, existing CNN-based methods show limitations in capturing spectral-wise similarity and long-range dependencies. Besides, the HSI information is modulated by a coded aperture (physical mask) in CASSI. Nonetheless, current algorithms have not fully explored the guidance effect of the mask for HSI restoration. In this paper, we propose a novel framework, Mask-guided Spectral-wise Transformer (MST), for HSI reconstruction. Specifically, we present a Spectral-wise Multi-head Self-Attention (S-MSA) that treats each spectral feature as a token and calculates self-attention along the spectral dimension. In addition, we customize a Mask-guided Mechanism (MM) that directs S-MSA to pay attention to spatial regions with high-fidelity spectral representations. Extensive experiments show that our MST significantly outperforms state-of-the-art (SOTA) methods on simulation and real HSI datasets while requiring dramatically cheaper computational and memory costs. Code and pre-trained models are available at https://github.com/caiyuanhao1998/MST/, CVPR 2022; The first Transformer-based method for snapshot compressive imaging

The rapid development of deep learning provides a better solution for the end-to-end reconstruction of hyperspectral image (HSI). However, existing learning-based methods have two major defects. Firstly, networks with self-attention usually sacrifice internal resolution to balance model performance against complexity, losing fine-grained high-resolution (HR) features. Secondly, even if the optimization focusing on spatial-spectral domain learning (SDL) converges to the ideal solution, there is still a significant visual difference between the reconstructed HSI and the truth. Therefore, we propose a high-resolution dual-domain learning network (HDNet) for HSI reconstruction. On the one hand, the proposed HR spatial-spectral attention module with its efficient feature fusion provides continuous and fine pixel-level features. On the other hand, frequency domain learning (FDL) is introduced for HSI reconstruction to narrow the frequency domain discrepancy. Dynamic FDL supervision forces the model to reconstruct fine-grained frequencies and compensate for excessive smoothing and distortion caused by pixel-level losses. The HR pixel-level attention and frequency-level refinement in our HDNet mutually promote HSI perceptual quality. Extensive quantitative and qualitative evaluation experiments show that our method achieves SOTA performance on simulated and real HSI datasets. Code and models will be released at https://github.com/caiyuanhao1998/MST, Comment: CVPR 2022

Existing leading methods for spectral reconstruction (SR) focus on designing deeper or wider convolutional neural networks (CNNs) to learn the end-to-end mapping from the RGB image to its hyperspectral image (HSI). These CNN-based methods achieve impressive restoration performance while showing limitations in capturing the long-range dependencies and self-similarity prior. To cope with this problem, we propose a novel Transformer-based method, Multi-stage Spectral-wise Transformer (MST++), for efficient spectral reconstruction. In particular, we employ Spectral-wise Multi-head Self-attention (S-MSA) that is based on the HSI spatially sparse while spectrally self-similar nature to compose the basic unit, Spectral-wise Attention Block (SAB). Then SABs build up Single-stage Spectral-wise Transformer (SST) that exploits a U-shaped structure to extract multi-resolution contextual information. Finally, our MST++, cascaded by several SSTs, progressively improves the reconstruction quality from coarse to fine. Comprehensive experiments show that our MST++ significantly outperforms other state-of-the-art methods. In the NTIRE 2022 Spectral Reconstruction Challenge, our approach won the First place. Code and pre-trained models are publicly available at https://github.com/caiyuanhao1998/MST-plus-plus., Winner of NTIRE 2022 Challenge on Spectral Reconstruction from RGB; The First Transformer-based Method for Spectral Reconstruction

Deep neural networks (DNNs) are widely used and demonstrated their power in many applications, such as computer vision and pattern recognition. However, the training of these networks can be time consuming. Such a problem could be alleviated by using efficient optimizers. As one of the most commonly used optimizers, stochastic gradient descent-momentum (SGD-M) uses past and present gradients for parameter updates. However, in the process of network training, SGD-M may encounter some drawbacks, such as the overshoot phenomenon. This problem would slow the training convergence. To alleviate this problem and accelerate the convergence of DNN optimization, we propose a proportional-integral-derivative (PID) approach. Specifically, we investigate the intrinsic relationships between the PID-based controller and SGD-M first. We further propose a PID-based optimization algorithm to update the network parameters, where the past, current, and change of gradients are exploited. Consequently, our proposed PID-based optimization alleviates the overshoot problem suffered by SGD-M. When tested on popular DNN architectures, it also obtains up to 50% acceleration with competitive accuracy. Extensive experiments about computer vision and natural language processing demonstrate the effectiveness of our method on benchmark data sets, including CIFAR10, CIFAR100, Tiny-ImageNet, and PTB. We have released the code at https://github.com/tensorboy/PIDOptimizer .

Depth images play an important role and are prevalently used in many computer vision and computational imaging tasks. However, due to the limitation of active sensing technology, the captured depth images in practice usually suffer from low resolution and noise, which prevents its further applications. To remedy this problem, in this paper, we first propose an adaptive data fidelity formulation to optimally generate each depth pixel from a mixture probability distribution, characterizing the similarity both in the depth map and the corresponding high-resolution guided color image. The proposed method is able to fit the distribution of the input depth signal as an optimization problem by maximizing the mixture probability. Furthermore, to promote the piecewise property that depth images exhibit, we propose a transferred graph Laplacian model as a regularization term, which is general and able to handle various depth recovery tasks such as super-resolution and denoising well. Specifically, each pixel within the recovered depth image is represented as a vertex in a graph with weights in connected edges representing the similarity between vertices. By minimizing the squared variations of the image signal, the task of depth image recovery can be converted to the problem of graph-based image filtering. Since the proposed graph Laplacian regularization model is able to fully exploit a priori information about the depth image, a much more accurate and robust estimation of the underlying depth can be obtained. Extensive experiment evaluations verify that the proposed method obtains recovered depth with higher quality in terms of both objective and subjective criteria, compared with most of the state-of-the-art methods.

This paper reviews the third biennial challenge on spectral reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image. This challenge presents the "ARAD_1K"data set: a new, larger-than-ever natural hyperspectral image data set containing 1,000 images. Challenge participants were required to recover hyper-spectral information from synthetically generated JPEG-compressed RGB images simulating capture by a known calibrated camera, operating under partially known parameters, in a setting which includes acquisition noise. The challenge was attended by 241 teams, with 60 teams com-peting in the final testing phase, 12 of which provided de-tailed descriptions of their methodology which are included in this report. The performance of these submissions is re-viewed and provided here as a gauge for the current state-of-the-art in spectral reconstruction from natural RGB images.

It is widely acknowledged that biological intelligence is capable of learning continually without forgetting previously learned skills. Unfortunately, it has been widely observed that many artificial intelligence techniques, especially (deep) neural network (NN)-based ones, suffer from catastrophic forgetting problem, which severely forgets previous tasks when learning a new one. How to train NNs without catastrophic forgetting, which is termed continual learning, is emerging as a frontier topic and attracting considerable research interest. Inspired by memory replay and synaptic consolidation mechanism in brain, in this article, we propose a novel and simple framework termed memory recall (MeRec) for continual learning with deep NNs. In particular, we first analyze the feature stability across tasks in NN and show that NN can yield task stable features in certain layers. Then, based on this observation, we use a memory module to keep the feature statistics (mean and std) for each learned task. Based on the memory and statistics, we show that a simple replay strategy with Gaussian distribution-based feature regeneration can recall and recover the knowledge from previous tasks. Together with the weight regularization, MeRec preserves weights learned from previous tasks. Based on this simple framework, MeRec achieved leading performance with extremely small memory budget (only two feature vectors for each class) for continual learning on CIFAR-10 and CIFAR-100 datasets, with at least 50% accuracy drop reduction after several tasks compared to previous state-of-the-art approaches.

The feedback mechanism in the human visual system extracts high-level semantics from noisy scenes. It then guides low-level noise removal, which has not been fully explored in image denoising networks based on deep learning. The commonly used fully-supervised network optimizes parameters through paired training data. However, unpaired images without noise-free labels are ubiquitous in the real world. Therefore, we proposed a multi-scale selective feedback network (MSFN) with the dual loss. We allow shallow layers to access valuable contextual information from the following deep layers selectively between two adjacent time steps. Iterative refinement mechanism can remove complex noise from coarse to fine. The dual regression is designed to reconstruct noisy images to establish closed-loop supervision that is training-friendly for unpaired data. We use the dual loss to optimize the primary clean-to-noisy task and the dual noisy-to-clean task simultaneously. Extensive experiments prove that our method achieves state-of-the-art results and shows better adaptability on real-world images than the existing methods.

Current methods of multi-person pose estimation typically treat the localization and the association of body joints separately. It is convenient but inefficient, leading to additional computation and a waste of time. This paper, however, presents a novel framework PoseDet (Estimating Pose by Detection) to localize and associate body joints simultaneously at higher inference speed. Moreover, we propose the keypoint-aware pose embedding to represent an object in terms of the locations of its keypoints. The proposed pose embedding contains semantic and geometric information, allowing us to access discriminative and informative features efficiently. It is utilized for candidate classification and body joint localization in PoseDet, leading to robust predictions of various poses. This simple framework achieves an unprecedented speed and a competitive accuracy on the COCO benchmark compared with state-of-the-art methods. Extensive experiments on the CrowdPose benchmark show the robustness in the crowd scenes. Source code is available., 10 pages, 5 figures

Biological activated carbon (BAC) filtration is usually considered to be able to decrease formation potentials (FPs) of disinfection by-products (DBPs) in drinking water treatment plant (DWTP). However, BAC filters with long running time may release microbial metabolites to effluents and therefore increase FPs of nitrogenous DBPs with high toxicity. To verify this hypothesis, this study continuously tracked BAC filters in a DWTP for one year, and assessed effects of old (running time 8–9 years) and new (running time 0–13 months) BAC filters on FPs of 15 regulated and unregulated DBPs. Results revealed that dissolved organic carbon (DOC) removal was slightly higher in the new BAC than the old one. All fluorescent components of dissolved organic matter evidently declined after new BAC filtration, but fulvic acid-like and soluble microbial product-like substances increased after old BAC filtration, which could be caused by microbial leakage. Correspondingly, new BAC filter generally removed more DBP FPs than the old one. 46.5% HAA7 FPs from chlorination and 44.3% THM4 FPs from chloramination were removed by new BAC filter. However, some DBP FPs, especially HAN FPs, were poorly removed or even increased by the old BAC filter. Proteobacteria could be a main contributor for DBP precursor removal in BAC filters. Herminiimonas, most abundant genera in new BAC filter, may explain its better DOC and UV254 removal performance and lower DBP FPs, while Bradyrhizobium, most abundant genera in old BAC filter, might produce more extracellular polymeric substances and therefore increased N-DBP FPs in old BAC effluent. This study provided insight into variations of DBP FPs and microbial communities in the new and old BAC filters, and will be helpful for the optimization of DWTP design and operation for public health.

Effectively imaging within volumetric scattering media is of great importance and challenging especially in macroscopic applications. Recent works have demonstrated the ability to image through scattering media or within the weak volumetric scattering media using spatial distribution or temporal characteristics of the scattered field. Here, we focus on imaging Lambertian objects embedded in highly scattering media, where signal photons are dramatically attenuated during propagation and highly coupled with background photons. We address these challenges by providing a time-to-space boundary migration model (BMM) of the scattered field to convert the scattered measurements in spectral form to the scene information in the temporal domain using all of the optical signals. The experiments are conducted under two typical scattering scenarios: 2D and 3D Lambertian objects embedded in the polyethylene foam and the fog, which demonstrate the effectiveness of the proposed algorithm. It outperforms related works including time gating in terms of reconstruction precision and scattering strength. Even though the proportion of signal photons is only 0.75%, Lambertian objects located at more than 25 transport mean free paths (TMFPs), corresponding to the round-trip scattering length of more than 50 TMFPs, can be reconstructed. Also, the proposed method provides low reconstruction complexity and millisecond-scale runtime, which significantly benefits its application.

Calcium imaging is inherently susceptible to detection noise especially when imaging with high frame rate or under low excitation dosage. We developed DeepCAD, a self-supervised learning method for spatiotemporal enhancement of calcium imaging without requiring any high signal-to-noise ratio (SNR) observations. Using this method, detection noise can be effectively suppressed and the imaging SNR can be improved more than tenfold, which massively improves the accuracy of neuron extraction and spike inference and facilitate the functional analysis of neural circuits.

In this paper, we propose a novel method called Residual Steps Network (RSN). RSN aggregates features with the same spatial size (Intra-level features) efficiently to obtain delicate local representations, which retain rich low-level spatial information and result in precise keypoint localization. Additionally, we observe the output features contribute differently to final performance. To tackle this problem, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations. Our approach won the 1st place of COCO Keypoint Challenge 2019 and achieves state-of-the-art results on both COCO and MPII benchmarks, without using extra training data and pretrained model. Our single model achieves 78.6 on COCO test-dev, 93.0 on MPII test dataset. Ensembled models achieve 79.2 on COCO test-dev, 77.1 on COCO test-challenge dataset. The source code is publicly available for further research at https://github.com/caiyuanhao1998/RSN/.

In this paper, we propose a novel method for 4D light-field (LF) depth estimation exploiting the special linear structure of an epipolar plane image (EPI) and locally linear embedding (LLE). Without high computational complexity, depth maps are locally estimated by locating the optimal slope of each line segmentation on the EPIs, which are projected by the corresponding scene points. For each pixel to be processed, we build and then minimize the matching cost that aggregates the intensity pixel value, gradient pixel value, spatial consistency, as well as reliability measure to select the optimal slope from a predefined set of directions. Next, a subangle estimation method is proposed to further refine the obtained optimal slope of each pixel. Furthermore, based on a local reliability measure, all the pixels are classified into reliable and unreliable pixels. For the unreliable pixels, LLE is employed to propagate the missing pixels by the reliable pixels based on the assumption of manifold preserving property maintained by natural images. We demonstrate the effectiveness of our approach on a number of synthetic LF examples and real-world LF data sets, and show that our experimental results can achieve higher performance than the typical and recent state-of-the-art LF stereo matching methods.

To improve imaging speed, multifocal excitation is widely adopted as a parallel strategy in laser-scanning microscopy. Specifically, axial multifocal microscopy is popular in neuroscience as it enables functional imaging of neurons in multiple depths simultaneously. However, previous phase searching algorithms for axial multi-foci generation generally generate foci of uniform intensities, which cannot compensate the scattering-induced power loss in deep tissue and causes inhomogeneous excitation. Here, we propose a novel adaptive optimization-based phase-searching method (AdaPS) to generate axial multi-foci with arbitrary intensity modulations for scattering-induced loss compensation. By adopting Adaptive Moment Estimation (Adam) as the searching algorithm, our method could escape from unsatisfactory local minima and stably converge to the optimal phase pattern with errors at least an order of magnitude lower. We validate AdaPS through both numerical simulations and experiments and demonstrate that AdaPS could provide uniform multi-depth imaging in scattering phantom and enable high-fidelity multi-depth recordings of neural network dynamics in mouse brain in vivo.