Super resolution image reconstruction allows the recovery of a high-resolution (HR) image from several low-resolution images that are noisy, blurred, and down sampled. In this paper, we present a joint formulation for a complex super-resolution problem in which the scenes contain multiple independently moving objects. This formulation is built upon the maximum a posteriori (MAP) framework, which judiciously combines motion estimation, segmentation, and super resolution together. A cyclic coordinate descent optimization procedure is used to solve the MAP formulation, in which the motion fields, segmentation fields, and HR images are found in an alternate manner given the two others, respectively. Specifically, the gradient-based methods are employed to solve the HR image and motion fields, and an iterated conditional mode optimization method to obtain the segmentation fields. The proposed algorithm has been tested using a synthetic image sequence, the "Mobile and Calendar" sequence, and the original "Motorcycle and Car" sequence. The experiment results and error analyses verify the efficacy of this algorithm.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/tip.2006.888334 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
SynPull: An advanced method for studying neurodegeneration-related aggregates in synaptosomes using super-resolution microscopy.
Cell Chem Biol
January 2025
Yusuf Hamied Department of Chemistry, University of Cambridge Cambridge CB2 1EW, UK; UK Dementia Research Institute at University of Cambridge Cambridge CB2 0XY, UK. Electronic address:
Synaptic dysfunction is a primary hallmark of both Alzheimer's and Parkinson's disease, leading to cognitive and behavioral decline. While alpha-synuclein, beta-amyloid, and tau are involved in the physiological functioning of synapses, their pathological aggregation has been linked to synaptopathology. The methodology for studying the small-soluble protein aggregates formed by these proteins is limited.
View Article and Find Full Text PDFProjecting future snow changes at kilometer scale for adaptation using machine learning and a CMIP6 multi-model ensemble.
Sci Total Environ
January 2025
Universidad de Santiago de Chile, Santiago, Chile.
Assessing future snow cover changes is challenging because the high spatial resolution required is typically unavailable from climate models. This study, therefore, proposes an alternative approach to estimating snow changes by developing a super-spatial-resolution downscaling model of snow depth (SD) for Japan using a convolutional neural network (CNN)-based method, and by downscaling an ensemble of models from the Coupled Model Intercomparison Project Phase 6 (CMIP6) dataset. After assessing the coherence of the observed reference SD dataset with independent observations, we leveraged it to train the CNN downscaling model; following its evaluation, we applied the trained model to CMIP6 climate simulations.
View Article and Find Full Text PDFMetasurface-Coated Liquid Microlens for Super Resolution Imaging.
Micromachines (Basel)
December 2024
State Key Laboratory for Manufacturing System Engineering, Xi'an Jiaotong University, Xi'an 710054, China.
Inspired by metasurfaces' control over light fields, this study created a liquid microlens coated with a layer of Au@TiO, Core-Shell nanospheres. Utilizing the surface plasmon resonance (SPR) effect of Au@TiO, Core-Shell nanospheres, and the formation of photonic nanojets (PNJs), this study aimed to extend the imaging system's cutoff frequency, improve microlens focusing, enhance the capture capability of evanescent waves, and utilize nanospheres to improve the conversion of evanescent waves into propagating waves, thus boosting the liquid microlens's super-resolution capabilities. The finite difference time domain (FDTD) method analyzed the impact of parameters including nanosphere size, microlens sample contact width, and droplet's initial contact angle on super-resolution imaging.
View Article and Find Full Text PDFMultifunctional Microflowers for Precise Optoacoustic Localization and Intravascular Magnetic Actuation In Vivo.
Adv Healthc Mater
January 2025
Institute for Biomedical Engineering and Institute of Pharmacology and Toxicology, Faculty of Medicine, University of Zürich, Winterthurerstrasse 190, Zurich, 8057, Switzerland.
Efficient drug delivery remains a significant challenge in modern medicine and pharmaceutical research. Micrometer-scale robots have recently emerged as a promising solution to enhance the precision of drug administration through remotely controlled navigation within microvascular networks. Real-time tracking is crucial for accurate guidance and confirmation of target arrival.
View Article and Find Full Text PDFUltrastructure expansion microscopy: Enlarging our perspective on apicomplexan cell division.
J Microsc
January 2025
Laboratory of Apicomplexan Biology, Institut Pasteur Montevideo, Montevideo, Uruguay.
Apicomplexans, a large phylum of protozoan intracellular parasites, well known for their ability to invade and proliferate within host cells, cause diseases with major health and economic impacts worldwide. These parasites are responsible for conditions such as malaria, cryptosporidiosis, and toxoplasmosis, which affect humans and other animals. Apicomplexans exhibit complex life cycles, marked by diverse modes of cell division, which are closely associated with their pathogenesis.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!