Related papers: Large model enhanced computational ghost imaging

Medical imaging is playing a more and more important role in clinics. However, there are several issues in different imaging modalities such as slow imaging speed in MRI, radiation injury in CT and PET. Therefore, accelerating MRI, reducing…

This study addresses construction site hazard identification by proposing a retrieval-augmented framework that enhances large language models (LLMs) without requiring fine-tuning. Current LLM-based approaches face limitations: image-text…

In recent years, deep neural networks, including Convolutional Neural Networks, Transformers, and State Space Models, have achieved significant progress in Remote Sensing Image (RSI) Super-Resolution (SR). However, existing SR methods…

Multimodal Large Language Models (MLLMs) demonstrate exceptional semantic reasoning but struggle with 3D spatial perception when restricted to pure RGB inputs. Despite leveraging implicit geometric priors from 3D reconstruction models,…

Open-vocabulary panoptic reconstruction is essential for advanced robotics perception and simulation. However, existing methods based on 3D Gaussian Splatting (3DGS) often struggle to simultaneously achieve geometric accuracy, coherent…

Leveraging large-scale Text-to-Image (TTI) models have become a common technique for generating exemplar or training dataset in the fields of image synthesis, video editing, 3D reconstruction. However, semantic structural visual…

High-resolution ghost image and ghost diffraction experiments are performed by using a single source of thermal-like speckle light divided by a beam splitter. Passing from the image to the diffraction result solely relies on changing the…

Classical ghost imaging is a new paradigm in imaging where the image of an object is not measured directly with a pixelated detector. Rather, the object is subject to a set of illumination patterns and the total interaction of the object,…

Motion modeling is critical in flow-based Video Frame Interpolation (VFI). Existing paradigms either consider linear combinations of bidirectional flows or directly predict bilateral flows for given timestamps without exploring favorable…

Reconstructing and understanding 3D structures from a limited number of images is a well-established problem in computer vision. Traditional methods usually break this task into multiple subtasks, each requiring complex transformations…

This study investigates the relationship between deep learning (DL) image reconstruction quality and anomaly detection performance, and evaluates the efficacy of an artificial intelligence (AI) assistant in enhancing radiologists'…

The power of DNNs relies heavily on the quantity and quality of training data. However, collecting and annotating data on a large scale is often expensive and time-consuming. To address this issue, we explore a new task, termed dataset…

Computational ghost imaging or single-pixel imaging enables the image formation of an unknown scene using a lens-free photodetector. In this Letter, we present a computational panoramic ghost imaging system that can achieve the full-color…

For remote sensing, high-resolution imaging techniques are helpful to catch more characteristic information of the target. We extend pseudo-thermal light ghost imaging to the area of remote imaging and propose a ghost imaging lidar system.…

Image super-resolution (SR) has attracted increasing attention due to its wide applications. However, current SR methods generally suffer from over-smoothing and artifacts, and most work only with fixed magnifications. This paper introduces…

In medical imaging, access to data is commonly limited due to patient privacy restrictions and the issue that it can be difficult to acquire enough data in the case of rare diseases.[1] The purpose of this investigation was to develop a…

Radiation damage is one of the most severe resolution limiting factors in x-ray imaging, especially relevant to biological samples. One way of circumventing this problem is to exploit correlation-based methods developed in quantum imaging.…

Deep neural networks (DNN) have achieved great success in image restoration. However, most DNN methods are designed as a black box, lacking transparency and interpretability. Although some methods are proposed to combine traditional…

We present an efficient and automatic approach for accurate reconstruction of instances of big 3D objects from multiple, unorganized and unstructured point clouds, in presence of dynamic clutter and occlusions. In contrast to conventional…

Unsupervised image segmentation is an important task in many real-world scenarios where labelled data is of scarce availability. In this paper we propose a novel approach that harnesses recent advances in unsupervised learning using a…