Michael W. Tao

Michael W. Tao

Auto-generated profile, based on publicly available information

Michael W. Tao

Otolaryngology, State University of New York Upstate Medical University, Syracuse, USA

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 April 2016 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
MTMichael W. Tao
Michael W. Tao
PSPratul P. Srinivasan
Pratul P. Srinivasan
SHSunil Hadap
Sunil Hadap
SRSzymon Rusinkiewicz
Szymon Rusinkiewicz
JMJitendra Malik
Jitendra Malik
RRRavi Ramamoorthi
Ravi Ramamoorthi
Light-field cameras are quickly becoming commodity items, with consumer and industrial applications. They capture many nearby views simultaneously using a single image with a micro-lens array, thereby providing a wealth of cues for depth recovery: defocus, correspondence, and shading. In particular, apart from conventional image shading, one can refocus images after acquisition, and shift one's viewpoint within the sub-apertures of the main lens, effectively obtaining multiple views. We present a principled algorithm for dense depth estimation that combines defocus and correspondence metrics. We then extend our analysis to the additional cue of shading, using it to refine fine details in the shape. By exploiting an all-in-focus image, in which pixels are expected to exhibit angular coherence, we define an optimization framework that integrates photo consistency, depth consistency, and shading consistency. We show that combining all three sources of information: defocus, correspondence, and shading, outperforms state-of-the-art light-field depth estimation algorithms in multiple scenarios.

13 October 2012 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
MTMichael W. Tao
Michael W. Tao
MJMicah K. Johnson
Micah K. Johnson
SPSylvain Paris
Sylvain Paris
Gradient-domain compositing is an essential tool in computer vision and its applications, e.g., seamless cloning, panorama stitching, shadow removal, scene completion and reshuffling. While easy to implement, these gradient-domain techniques often generate bleeding artifacts where the composited image regions do not match. One option is to modify the region boundary to minimize such mismatches. However, this option may not always be sufficient or applicable, e.g., the user or algorithm may not allow the selection to be altered. We propose a new approach to gradient-domain compositing that is robust to inaccuracies and prevents color bleeding without changing the boundary location. Our approach improves standard gradient-domain compositing in two ways. First, we define the boundary gradients such that the produced gradient field is nearly integrable. Second, we control the integration process to concentrate residuals where they are less conspicuous. We show that our approach can be formulated as a standard least-squares problem that can be solved with a sparse linear system akin to the classical Poisson equation. We demonstrate results on a variety of scenes. The visual quality and run-time complexity compares favorably to other approaches.

7 October 2022 in Cureus
Verified
Journal Article
Open access
MGMitchell R. Gore
Mitchell R. Gore
FEFung Ethan
Fung Ethan
MTMichael Tao
Michael Tao
Asthma, Allergic rhinitis (AR), Chronic Obstructive Pulmonary Disease (COPD), Eczema, and Chronic Rhinosinusitis with Sinonasal Polyposis (CRSwNP) are illnesses often characterized by type 2 (T2) inflammation, wherein T helper (Th) cells release pro-inflammatory cytokines such as IL (interleukin)-4, IL-5, IL-9, and IL-13. This response may also promote the production of IgE and an increase in/activation of serum eosinophils. In the aforementioned type 2 inflammatory diseases, this immune response can cause excess mucous production, inflammation of the airways, other atopic responses when patients are exposed to certain environmental allergic triggers. Relatively new biologic monoclonal antibody therapies such as dupilumab (blocks IL-4 and IL-13), benralizumab (blocks IL-5), mepolizumab (blocks IL-5), and omalizumab (blocks IgE Fc/fragment of crystallization region) offer novel therapeutic targets that more specifically and directly block type 2 inflammatory responses. To examine the effect of monoclonal antibody biologic therapies on patient indicators of type 2 inflammation, a retrospective analysis of 193 patients on biologic therapy was conducted, and these patients were compared to 48 control patients with type 2 inflammatory diseases who did not initiate biologic therapy. Total Lund-MacKay radiographic score, FEV1 (forced expiratory volume in the first second), FEF25-75 (forced expiratory flow from 25-75% of the forced vital capacity curve), annualized pulmonary exacerbations, oral corticosteroid dose, and serum eosinophils were recorded at baseline (zero months), and at three, six, nine, and twelve months after initiation of biologic therapy. Least squares mean data and the percent change from the baseline of least squares mean for the biologic and control groups were compared. Omalizumab was the most common biologic therapy prescribed. Control patients were younger than patients who initiated biologic therapy. Patients on biologic therapy had statistically significant reductions in Lund-MacKay score, improvements in FEV1 and FEF25-75, reductions in serum IgE levels, and reductions in serum Eosinophils. Patients on biologic therapy also had statistically significant reductions in annualized pulmonary exacerbations and oral corticosteroid dose compared to controls. Patients with a variety of type 2 inflammatory conditions appear to have significant improvements in lung function, radiographic sinusitis, and serum markers of type 2 inflammation after initiation of biologic therapy versus controls. These therapeutic medications appear to significantly improve type 2 inflammatory disease course in patients who can tolerate these medications.