- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) - Orlando, FL, USA (2018.12.17-2018.12.20)] 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) - GAN-Based Super Resolution for Accurate 3D Surface Reconstruction from Light Field Skin Images Towards Haptic Palpation
摘要： The development of vision technology for observation of skin surface and diagnosis of skin disease for preventing secondary infections caused by direct skin touch has consistently been in the medical field spotlight. Many studies have been conducted to acquire three dimensional (3D) data through stereo images, multiple images, and lasers because (3D) data of in-vivo skin image is essential for accurate medical diagnosis. However, stereo vision systems or 3D laser systems for obtaining 3D information require high cost and have high computational complexity, and hence they have not been used universally. Additionally, the use of such systems is still not preferred in the medical field due to limitations on visual decision making. Therefore, a haptic diagnosis system that can blend vision information from a camera and palpation information from a dermatologist has been considered. In this study, we propose a 3D skin surface reconstruction method using a light field camera for haptic rendering and palpation. To achieve this goal, we addressed the low resolution problem, which has been consistently present in light field cameras, through the generative adversarial nets (GANs)-based super resolution method, and exploited the light field system which has been applied only to the object scene for obtaining 3D skin surface texture. Experimental results show that the method proposed in this study is promising and offers sufficient potential for haptic diagnosis.
关键词： Light field images,deep learning,3D skin surface reconstruction,disparity map,haptic palpation,super resolution
更新于2025-09-19 17:15:36
-
Light Field Super-Resolution using a Low-Rank Prior and Deep Convolutional Neural Networks
摘要： Light ?eld imaging has recently known a regain of interest due to the availability of practical light ?eld capturing systems that offer a wide range of applications in the ?eld of computer vision. However, capturing high-resolution light ?elds remains technologically challenging since the increase in angular resolution is often accompanied by a signi?cant reduction in spatial resolution. This paper describes a learning-based spatial light ?eld super-resolution method that allows the restoration of the entire light ?eld with consistency across all angular views. The algorithm ?rst uses optical ?ow to align the light ?eld and then reduces its angular dimension using low-rank approximation. We then consider the linearly independent columns of the resulting low-rank model as an embedding, which is restored using a deep convolutional neural network (DCNN). The super-resolved embedding is then used to reconstruct the remaining views. The original disparities are restored using inverse warping where missing pixels are approximated using a novel light ?eld inpainting algorithm. Experimental results show that the proposed method outperforms existing light ?eld super-resolution algorithms, achieving PSNR gains of 0.23 dB over the second best performing method. The performance is shown to be further improved using iterative back-projection as a post-processing step.
关键词： Low-Rank Matrix Approximation,Super-Resolution,Light Field,Deep Convolutional Neural Networks
更新于2025-09-19 17:15:36
-
Bioinspired magnetic nanoparticles as multimodal photoacoustic, photothermal and photomechanical contrast agents
摘要： Nanoparticles from magnetotactic bacteria have been used in conventional imaging, drug delivery, and magnetic manipulations. Here, we show that these natural nanoparticles and their bioinspired hybrids with near-infrared gold nanorods and folic acid can serve as molecular high-contrast photoacoustic probes for single-cell diagnostics and as photothermal agents for single-cell therapy using laser-induced vapor nanobubbles and magnetic field as significant signal and therapy amplifiers. These theranostics agents enable the detection and photomechanical killing of triple negative breast cancer cells that are resistant to conventional chemotherapy, with just one or a few low-energy laser pulses. In studies in vivo, we discovered that circulating tumor cells labeled with the nanohybrids generate transient ultrasharp photoacoustic resonances directly in the bloodstream as the basis for new super-resolution photoacoustic flow cytometry in vivo. These properties make natural and bioinspired magnetic nanoparticles promising biocompatible, multimodal, high-contrast, and clinically relevant cellular probes for many in vitro and in vivo biomedical applications.
关键词： theranostics,super-resolution,contrast agents,photomechanical,photoacoustic,magnetic nanoparticles,photothermal,circulating tumor cells,bioinspired,magnetotactic bacteria
更新于2025-09-19 17:15:36
-
Fluorogenic probes for super-resolution microscopy
摘要： Fluorogenic probes efficiently reduce non-specific background signals, which often results in highly improved signal-to-noise ratios. Although this implies improved resolution, fluorogenic probes in the context of super-resolution microscopy are somewhat overlooked. Several excellent reviews summarize recent developments in SRM techniques, labeling techniques or different aspects of small synthetic fluorophores, however there is no comprehensive review on fluorogenic probes suitable for super-resolution microscopy. Herein we wish to fill this gap by providing the readers with an up-to-date summary of fluorogenic probes applied to super-resolution imaging of cellular structures.
关键词： signal-to-noise ratio,background reduction,super-resolution microscopy,cellular imaging,fluorogenic probes
更新于2025-09-19 17:15:36
-
[Lecture Notes in Computer Science] Computer Vision – ECCV 2018 Workshops Volume 11133 (Munich, Germany, September 8-14, 2018, Proceedings, Part V) || Deep Residual Attention Network for Spectral Image Super-Resolution
摘要： Spectral imaging sensors often suffer from low spatial resolution, as there exists an essential tradeoff between the spectral and spatial resolutions that can be simultaneously achieved, especially when the temporal resolution needs to be retained. In this paper, we propose a novel deep residual attention network for the spatial super-resolution (SR) of spectral images. The proposed method extends the classic residual network by (1) directly using the 3D low-resolution (LR) spectral image as input instead of upsampling the 2D bandwise images separately, and (2) integrating the channel attention mechanism into the residual network. These two operations fully exploit the correlations across both the spectral and spatial dimensions and greatly promote the performance of spectral image SR. In addition, for the scenario when stereo pairs of LR spectral and high-resolution (HR) RGB measurements are available, we design a fusion framework based on the proposed network. The spatial resolution of the spectral input is enhanced in one branch, while the spectral resolution of the RGB input is enhanced in the other. These two branches are then fused together through the attention mechanism again to reconstruct the final HR spectral image, which achieves further improvement compared to using the single LR spectral input. Experimental results demonstrate the superiority of the proposed method over plain residual networks, and our method is one of the winning solutions in the PIRM 2018 Spectral Super-resolution Challenge.
关键词： Spectral image,Super-resolution,Channel attention
更新于2025-09-19 17:15:36
-
[Lecture Notes in Computer Science] Computer Vision – ECCV 2018 Workshops Volume 11133 (Munich, Germany, September 8-14, 2018, Proceedings, Part V) || Multi-modal Spectral Image Super-Resolution
摘要： Recent advances have shown the great power of deep convolutional neural networks (CNN) to learn the relationship between low and high-resolution image patches. However, these methods only take a single-scale image as input and require large amount of data to train without the risk of overfitting. In this paper, we tackle the problem of multi-modal spectral image super-resolution while constraining ourselves to a small dataset. We propose the use of different modalities to improve the performance of neural networks on the spectral super-resolution problem. First, we use multiple downscaled versions of the same image to infer a better high-resolution image for training, we refer to these inputs as a multi-scale modality. Furthermore, color images are usually taken at a higher resolution than spectral images, so we make use of color images as another modality to improve the super-resolution network. By combining both modalities, we build a pipeline that learns to super-resolve using multi-scale spectral inputs guided by a color image. Finally, we validate our method and show that it is economic in terms of parameters and computation time, while still producing state-of-the-art results (Code at https://github.com/IVRL/Multi-Modal-Spectral-Image-Super-Resolution).
关键词： Image completion,Spectral reconstruction,Spectral image super-resolution,Multi-modality,Residual learning
更新于2025-09-19 17:15:36
-
Lifetime super-resolution optical fluctuation imaging
摘要： In this paper, we propose a promising super-resolution imaging scheme in fluorescence lifetime domain (lifetime super-resolution optical fluctuation imaging, ltSOFI). ltSOFI has the potential to obtain super-resolution images by taking advantage of fluorescence lifetime blinking under wide-field lifetime detection. The proof-of-concept for ltSOFI was demonstrated through numerical simulation of high-order cumulant analysis on fluorescence lifetime blinking emitters. As a tentative experimental demonstration, we obtained super-resolution lifetime imaging from time-lapse FLIM recording of HeLa cells expressing a cAMP sensor using ltSOFI method. ltSOFI is expected to initiate a new dimension in the lifetime domain for blinking-based super-resolution microscopy.
关键词： fluorescence fluctuation,lifetime blinking,super-resolution
更新于2025-09-19 17:15:36
-
On the impact of competing intra- and intermolecular triplet-state quenching on photobleaching and photoswitching kinetics of organic fluorophores
摘要： While buffer cocktails remain the most commonly used method for photostabilization and photoswitching of fluorescent markers, intramolecular triplet-state quenchers emerge as an alternative strategy to impart fluorophores with 'self-healing' or even functional properties such as photoswitching. In this contribution, we evaluated combinations of both approaches and show that inter- and intramolecular triplet-state quenching processes compete with each other. We find that although the rate of triplet-state quenching is additive, the photostability is limited by the faster pathway. Often intramolecular processes dominate the photophysical situation for combinations of covalently-linked and solution-based photostabilizers and photoswitching agents. Furthermore we show that intramolecular photostabilizers can protect fluorophores from reversible off-switching events caused by solution-additives, which was previously misinterpreted as photobleaching. Our studies also provide practical guidance for usage of photostabilizer–dye conjugates for STORM-type super-resolution microscopy permitting the exploitation of their improved photophysics for increased spatio-temporal resolution. Finally, we provide evidence that the biochemical environment, e.g., proximity of aromatic amino-acids such as tryptophan, reduces the photostabilization efficiency of commonly used buffer cocktails. Not only have our results important implications for a deeper mechanistic understanding of self-healing dyes, but they will provide a general framework to select label positions for optimal and reproducible photostability or photoswitching kinetics in different biochemical environments.
关键词： photoswitching,intramolecular quenching,self-healing dyes,super-resolution microscopy,intermolecular quenching,photostabilization,fluorophores,triplet-state quenching,STORM
更新于2025-09-19 17:15:36
-
[IEEE 2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP) - Le gosier, Guadeloupe (2019.12.15-2019.12.18)] 2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP) - Is There Any Recovery Guarantee with Coupled Structured Matrix Factorization for Hyperspectral Super-Resolution?
摘要： Coupled structured matrix factorization (CoSMF) for hyperspectral super-resolution (HSR) has recently drawn significant interest in hyperspectral imaging for remote sensing. Presently there are very few studies on the theoretical recovery guarantees of CoSMF. This paper makes one such endeavor by considering the CoSMF formulation by Wei et al., which, simply speaking, is similar to coupled non-negative matrix factorization. Assuming no noise, we show sufficient conditions under which the globally optimal solution to the CoSMF problem is guaranteed to deliver certain recovery accuracies. Our analysis suggests that sparsity and the pure-pixel (or separability) condition play a hidden role in enabling CoSMF to achieve some good recovery characteristics.
关键词： coupled structured matrix factorization,hyperspectral super-resolution,recovery guarantee
更新于2025-09-19 17:13:59
-
[IEEE 2019 Conference on Lasers and Electro-Optics Europe & European Quantum Electronics Conference (CLEO/Europe-EQEC) - Munich, Germany (2019.6.23-2019.6.27)] 2019 Conference on Lasers and Electro-Optics Europe & European Quantum Electronics Conference (CLEO/Europe-EQEC) - Multi-Qubit Registers of Individually Addressable Solid-State Defect Centers
摘要： Mesoscopic ensembles of qubits offer a platform for near-term applications in quantum technologies, as well as for studying many-body physics. Key in exploiting these systems is the ability to coherently control constituent qubits in a manner that leaves the quantum states of neighboring qubits unperturbed. Atom-like emitters in solids have emerged as a promising platform for computing, communications, and sensing. In particular, their long coherence times, coherent optical transitions, and the ability to couple to nearby long-lived nuclear spins make them excellent candidates for building medium-scale registers of coupled qubits. Here, we present progress towards producing and controlling such individually addressable ensembles. Our approach relies on the natural inhomogeneous distribution of optical transitions for solid-state color centers. This distribution allows us to excite individual centers even in tightly-grouped clusters. With this, we first demonstrate super-resolution localization and readout of individual nitrogen vacancy (NV) centers in diamond. We probe a system of three NV centers, demonstrating localization with a mean precision of 0.74 nm. While super-resolution imaging of NV centers has been achieved with other techniques, our approach uniquely allows for individual readout of single NVs in a cluster in a manner that maintains the states of nearby spins. We perform simultaneous control of two spin populations in a cluster of NVs, demonstrating preservation of coherence of one population during the optical readout of another. Lastly, we discuss recent work towards scalable creation of such clusters and techniques for producing systems of coupled spins with various defect centers.
关键词： spin-spin coupling,quantum technologies,super-resolution localization,qubits,solid-state color centers,nitrogen vacancy centers,many-body physics,atom-like emitters
更新于2025-09-16 10:30:52