Impact of Image Resolution on Deep Learning Performance in Endoscopy Image Classification: An Experimental Study Using a Large Dataset of Endoscopic Images [PDF]
Diagnostics, 2021 Recent trials have evaluated the efficacy of deep convolutional neural network (CNN)-based AI systems to improve lesion detection and characterization in endoscopy.
Vajira Thambawita +5 more
doaj +3 more sources
SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution [PDF]
Computer Vision and Pattern Recognition, 2023 Owe to the powerful generative priors, the pretrained text-to-image (T2I) diffusion models have become increasingly popular in solving the real-world image super-resolution problem.
Rongyuan Wu +5 more
openalex +3 more sources
The Effect of Image Resolution on Deep Learning in Radiography. [PDF]
Radiol Artif Intell, 2020 Purpose To examine variations of convolutional neural network (CNN) performance for multiple chest radiograph diagnoses and image resolutions. Materials and Methods This retrospective study examined CNN performance using the publicly available National
Sabottke CF, Spieler BM.
europepmc +2 more sources
The Importance of Image Resolution in Building Deep Learning Models for Medical Imaging. [PDF]
Radiol Artif Intell, 2020 D learning with convolutional neural networks (CNNs) has shown tremendous success in classifying images, as we have seen with the ImageNet competition (1), which consists of millions of everyday color images, such as animals, vehicles, and natural ...
Lakhani P.
europepmc +2 more sources
Mastcam Image Resolution Enhancement with Application to Disparity Map Generation for Stereo Images with Different Resolutions [PDF]
Sensors, 2019 In this paper, we introduce an in-depth application of high-resolution disparity map estimation using stereo images from Mars Curiosity rover’s Mastcams, which have two imagers with different resolutions.
Bulent Ayhan, Chiman Kwan
doaj +2 more sources
High-Resolution Image Synthesis with Latent Diffusion Models [PDF]
Computer Vision and Pattern Recognition, 2021 By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a guiding mechanism
Robin Rombach +4 more
semanticscholar +1 more source
Restormer: Efficient Transformer for High-Resolution Image Restoration [PDF]
Computer Vision and Pattern Recognition, 2021 Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoration and related tasks.
Syed Waqas Zamir +5 more
semanticscholar +1 more source
Monkey: Image Resolution and Text Label are Important Things for Large Multi-Modal Models [PDF]
Computer Vision and Pattern Recognition, 2023 Large Multimodal Models (LMMs) have shown promise in vision-language tasks but struggle with high-resolution input and detailed scene understanding. Addressing these challenges, we introduce Monkey to enhance LMM capabilities.
Zhang Li +8 more
semanticscholar +1 more source
Image Super-Resolution via Iterative Refinement [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021 We present SR3, an approach to image Super-Resolution via Repeated Refinement. SR3 adapts denoising diffusion probabilistic models (Ho et al. 2020), (Sohl-Dickstein et al.
Chitwan Saharia +5 more
semanticscholar +1 more source
Super-resolution Ultrasound Imaging [PDF]
Ultrasound in Medicine & Biology, 2020 Ultrasound in medicine & biology 46(4), 865-891 (2020).
Christensen-Jeffries, Kirsten +11 more
openaire +7 more sources