Related papers: Multi-layer 5D Optical Data Storage: Mathematical …
Fine-grained visual recognition is challenging because it highly relies on the modeling of various semantic parts and fine-grained feature learning. Bilinear pooling based models have been shown to be effective at fine-grained recognition,…
Learning and analyzing 3D point clouds with deep networks is challenging due to the sparseness and irregularity of the data. In this paper, we present a data-driven point cloud upsampling technique. The key idea is to learn multi-level…
Lensless cameras provide a framework to build thin imaging systems by replacing the lens in a conventional camera with an amplitude or phase mask near the sensor. Existing methods for lensless imaging can recover the depth and intensity of…
3D city models can be generated from aerial images. However, the calculated DSMs suffer from noise, artefacts, and data holes that have to be manually cleaned up in a time-consuming process. This work presents an approach that automatically…
Data-driven developments in lensless imaging, such as machine learning-based reconstruction algorithms, require large datasets. In this work, we introduce a data acquisition pipeline that can capture from multiple lensless imaging systems…
Super-resolution reconstruction techniques entail the utilization of software algorithms to transform one or more sets of low-resolution images captured from the same scene into high-resolution images. In recent years, considerable…
In single-particle cryo-electron microscopy (cryo-EM), the efficient determination of orientation parameters for 2D projection images poses a significant challenge yet is crucial for reconstructing 3D structures. This task is complicated by…
We have developed a method for the linear reconstruction of an image from undersampled, dithered data. The algorithm, known as Variable-Pixel Linear Reconstruction, or informally as Drizzle, preserves photometry and resolution, can weight…
Neural networks have been notorious for being computationally expensive. This is mainly because neural networks are often over-parametrized and most likely have redundant nodes or layers as they are getting deeper and wider. Their demand…
As an important branch of photoacoustic microscopy, optical-resolution photoacoustic microscopy suffers from limited depth of field due to the strongly focused laser beam. In this work, a 3D information fusion algorithm based on 3D…
Image classification models often demonstrate unstable performance in real-world applications due to variations in image information, driven by differing visual perspectives of subject objects and lighting discrepancies. To mitigate these…
Eyeframe lens tracing is an important process in the optical industry that requires sub-millimeter precision to ensure proper lens fitting and optimal vision correction. Traditional frame tracers rely on mechanical tools that need precise…
Bidirectional recurrent neural networks (bi-RNNs), in particular, bidirectional long short term memory (bi-LSTM), bidirectional gated recurrent unit, and convolutional bi-LSTM models have recently attracted attention for nonlinearity…
While diffusion-based generative models have made significant strides in visual content creation, conventional approaches face computational challenges, especially for high-resolution images, as they denoise the entire image from noisy…
The development of large-scale 3D scene reconstruction and novel view synthesis methods mostly rely on datasets comprising perspective images with narrow fields of view (FoV). While effective for small-scale scenes, these datasets require…
We introduce a new multiscale restoration algorithm for images with few photons counts and its use for denoising XMM data. We use a thresholding of the wavelet space so as to remove the noise contribution at each scale while preserving the…
Convolutional neural networks are state-of-the-art for various segmentation tasks. While for 2D images these networks are also computationally efficient, 3D convolutions have huge storage requirements and require long training time. To…
Complex systems such as aircraft engines, turbines, and industrial machinery often operate under dynamically changing conditions. These varying operating conditions can substantially influence degradation behavior and make prognostic…
Visual restoration and recognition are traditionally addressed in pipeline fashion, i.e. denoising followed by classification. Instead, observing correlations between the two tasks, for example clearer image will lead to better…
X-ray polarization is a powerful tool for unveiling the anisotropic characteristics of high-energy celestial objects. We present a novel imaging reconstruction method designed for hard X-ray polarimeters employing a Si CMOS sensor and coded…