Related papers: PISE: Physics-Anchored Semantically-Enhanced Deep …
This paper proposes a biologically-inspired low-level spatiochromatic-model-based similarity method (BLeSS) to assist full-reference image-quality estimators that originally oversimplify color perception processes. More specifically, the…
Recently, Deep Image Prior (DIP) has demonstrated strong capabilities for solving inverse imaging problems (IIPs) by optimizing a randomly initialized convolutional neural network in a training-data-free regime. However, DIP suffers from…
Whole slide images (WSIs) in computational pathology (CPath) pose a major computational challenge due to their gigapixel scale, often requiring the processing of tens to hundreds of thousands of high-resolution patches per slide. This…
We propose a novel active learning strategy for regression, which is model-agnostic, robust against model mismatch, and interpretable. Assuming that a small number of initial samples are available, we derive the optimal training density…
Modern photon-counting sensors are increasingly dominated by Poisson noise, yet conventional feature-specific imaging (FSI), based on principal component analysis (PCA), is optimized for additive Gaussian noise and variance preservation…
Automated image captioning has the potential to be a useful tool for people with vision impairments. Images taken by this user group are often noisy, which leads to incorrect and even unsafe model predictions. In this paper, we propose a…
We investigate the ability to reconstruct and derive spatial structure from sparsely sampled 3D piezoresponse force microcopy data, captured using the band-excitation (BE) technique, via Gaussian Process (GP) methods. Even for weakly…
The existing segmentation techniques require high-fidelity images as input to perform semantic segmentation. Since the segmentation results contain most of edge information that is much less than the acquired images, the throughput gap…
A plethora of recent research has focused on improving the memory footprint and inference speed of deep networks by reducing the complexity of (i) numerical representations (for example, by deterministic or stochastic quantization) and (ii)…
We propose a method for lossy image compression based on recurrent, convolutional neural networks that outperforms BPG (4:2:0 ), WebP, JPEG2000, and JPEG as measured by MS-SSIM. We introduce three improvements over previous research that…
Traditionally, neutron-$\gamma$ discrimination in organic scintillators relies on techniques such as time-of-flight (ToF) selection and pulse-shape discrimination (PSD). However, particle identification through graphical cuts remains…
In this paper, we propose a novel framework for speech-image retrieval. We utilize speech-image contrastive (SIC) learning tasks to align speech and image representations at a coarse level and speech-image matching (SIM) learning tasks to…
We consider the challenging blind denoising problem for Poisson-Gaussian noise, in which no additional information about clean images or noise level parameters is available. Particularly, when only "single" noisy images are available for…
Temporal Ghost Imaging (TGI), which reconstructs fast temporal signals using a slow detector, holds significant potential in optical communication, high-speed imaging, and quantum information processing. However, achieving high-quality…
The unsupervised 3D object detection is to accurately detect objects in unstructured environments with no explicit supervisory signals. This task, given sparse LiDAR point clouds, often results in compromised performance for detecting…
Coincidence imaging, also known as ghost imaging, is a technique that exploits correlations between two particles to reconstruct information about a specimen. The particle that relays the spatial information about the object remains…
Why rely on dense neural networks and then blindly sparsify them when prior knowledge about the problem structure is already available? Many inverse problems admit algorithm-unrolled networks that naturally encode physics and sparsity. In…
Panoptic segmentation is a key enabler for robotic perception, as it unifies semantic understanding with object-level reasoning. However, the increasing complexity of state-of-the-art models makes them unsuitable for deployment on…
Structured illumination microscopy (SIM) improves resolution by down-modulating high-frequency information of an object to fit within the passband of the optical system. Generally, the reconstruction process requires prior knowledge of the…
Techniques based on classical and quantum correlations in light beams, such as ghost imaging, allow us to overcome many limitations of conventional imaging and sensing protocols. Despite their advantages, applications of such techniques are…