Results 71 to 80 of about 11,065 (211)
Applying single-image super-resolution for the enhancement of deep-water bathymetry
Heliyon, 2019 We present research using single-image super-resolution (SISR) algorithms to enhance knowledge of the seafloor using the 1-minute GEBCO 2014 grid when 100m grids from high-resolution sonar systems are available for training.
Kristen Nock +5 more
doaj +1 more source
High Quality Image Interpolation via Local Autoregressive and Nonlocal 3-D Sparse Regularization
, 2012 In this paper, we propose a novel image interpolation algorithm, which is formulated via combining both the local autoregressive (AR) model and the nonlocal adaptive 3-D sparse model as regularized constraints under the regularization framework ...
Fan, Xiaopeng +5 more
core +2 more sources
Parts Surface Defect Detection Algorithm Based on Improved YOLOv8s
Engineering Reports, Volume 8, Issue 1, January 2026.Enhanced YOLOv8s for real‐time surface defect detection: An improved YOLOv8s deep learning model is developed for detecting fatigue and linear cracks on part surfaces. Trained on a high‐resolution crack dataset with diverse environmental and texture conditions, the model achieves mAP@0.5 = 0.9626, mAP@0.5:0.95 = 0.7803, Precision = 0.926, and Recall ...
Zhe Sun +3 more
wiley +1 more source
Image Super-Resolution via Dual-Dictionary Learning And Sparse Representation
, 2012 Learning-based image super-resolution aims to reconstruct high-frequency (HF) details from the prior model trained by a set of high- and low-resolution image patches.
Ma, Siwei +4 more
core +1 more source
Progress in Photovoltaics: Research and Applications, Volume 34, Issue 1, Page 116-131, January 2026.Machine learning (ML) enables fast and reliable prediction of series resistance and dark saturation current maps from voltage‐dependent electroluminescence of silicon solar cells. Two ML algorithms, a multilayer perceptron (MLP) and a modified U‐NET (mU‐NET), are analyzed. They are compared to nonlinear least squares fitting to assess their performance.
Erell Laot +3 more
wiley +1 more source
Enhanced Deep Residual Networks for Single Image Super-Resolution
, 2017 Recent research on super-resolution has progressed with the development of deep convolutional neural networks (DCNN). In particular, residual learning techniques exhibit improved performance.
Kim, Heewon +4 more
core +1 more source
Bilinear and Bicubic Interpolations for Image Presentation of Mechanical Stress and Temperature Distribution [PDF]
, 2022 Manikanta B. Pithani +2 more
openalex +1 more source
Journal of Geophysical Research: Solid Earth, Volume 131, Issue 1, January 2026.Abstract What happens when subduction stops is a key, but poorly understood, part of the tectonic cycle. Northern Borneo (Sabah) with a complex geological history of multiple episodes of subduction, magmatism, uplift, subsidence, and extension since the Mesozoic, is an ideal location for studying post‐subduction processes.
Amy Gilligan +6 more
wiley +1 more source
Smooth parametric surfaces and n-sided patches [PDF]
, 1989 The theory of 'geometric continuity' within the subject of CAGD is reviewed. In particular, we are concerned with how parametric surface patches for CAGD can be pieced together to form a smooth Ck surface.
Gregory, JA, Lau, VKH, Zhou, J
core
Multigrid Backprojection Super-Resolution and Deep Filter Visualization
, 2019 We introduce a novel deep-learning architecture for image upscaling by large factors (e.g. 4x, 8x) based on examples of pristine high-resolution images. Our target is to reconstruct high-resolution images from their downscale versions.
Liu, Hanwen +2 more
core +1 more source