Results 11 to 20 of about 9,200 (172)

ADE-CycleGAN: A Detail Enhanced Image Dehazing CycleGAN Network

Sensors, 2023
The preservation of image details in the defogging process is still one key challenge in the field of deep learning. The network uses the generation of confrontation loss and cyclic consistency loss to ensure that the generated defog image is similar to ...
Bingnan Yan, Zhaozhao Yang, Huizhu Sun, Conghui Wang   +3 more
doaj   +3 more sources

Mol-CycleGAN - a generative model for molecular optimization [PDF]

Journal of Cheminformatics, 2019
Designing a molecule with desired properties is one of the biggest challenges in drug development, as it requires optimization of chemical compound structures with respect to many complex properties.
A Gupta, D Rogers, E Ratti, H Chen, J Bajorath, J Besnard, MH Segler, R Winter, T Sterling, VS Rao   +9 more
core   +9 more sources

POCS-Augmented CycleGAN for MR Image Reconstruction [PDF]

Applied Sciences, 2021
Recent years have seen increased research interest in replacing the computationally intensive Magnetic resonance (MR) image reconstruction process with deep neural networks.
Yiran Li, Hanlu Yang, Danfeng Xie, David Dreizin, Fuqing Zhou, Ze Wang   +5 more
doaj   +3 more sources

CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-Spectrogram Conversion [PDF]

Interspeech 2020, 2020
Non-parallel voice conversion (VC) is a technique for learning mappings between source and target speeches without using a parallel corpus. Recently, cycle-consistent adversarial network (CycleGAN)-VC and CycleGAN-VC2 have shown promising results regarding this problem and have been widely used as benchmark methods.
Kaneko, Takuhiro, Kameoka, Hirokazu, Tanaka, Kou, Hojo, Nobukatsu   +3 more
openaire   +2 more sources

Enhancing CBCT-based CT synthesis using planning MRI in adaptive proton therapy for head cancer: A deep learning approach. [PDF]

J Appl Clin Med Phys
Abstract Background Proton therapy (PT) is recognized as a superior treatment for head cancer (HC) due to its precision and minimal damage to surrounding healthy tissues, relying on computed tomography (CT) data for dose calculations. Adaptive proton therapy (APT) is crucial to address changes in patient anatomy during treatment and update dose ...
Molina-Maza JM, Viar-Hernandez D, Rodriguez-Gonzalez B, Sequeiro-Gonzalez J, Vera-Sanchez JA, Mazal A, Malpica N, Torrado-Carvajal A, Perez-Moreno JM, Rodriguez-Vila B.   +9 more
europepmc   +2 more sources

CycleGAN for interpretable online EMT compensation [PDF]

International Journal of Computer Assisted Radiology and Surgery, 2021
Abstract Purpose Electromagnetic tracking (EMT) can partially replace X-ray guidance in minimally invasive procedures, reducing radiation in the OR. However, in this hybrid setting, EMT is disturbed by metallic distortion caused by the X-ray device.
Krumb, Henry, Das, Dhritimaan, Chadda, Romol, Mukhopadhyay, Anirban   +3 more
openaire   +5 more sources

Cyclegan-VC2: Improved Cyclegan-based Non-parallel Voice Conversion [PDF]

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019
Non-parallel voice conversion (VC) is a technique for learning the mapping from source to target speech without relying on parallel data. This is an important task, but it has been challenging due to the disadvantages of the training conditions. Recently, CycleGAN-VC has provided a breakthrough and performed comparably to a parallel VC method without ...
Kaneko, Takuhiro, Kameoka, Hirokazu, Tanaka, Kou, Hojo, Nobukatsu   +3 more
openaire   +2 more sources

Contrastive virtual staining enhances deep learning-based PDAC subtyping from H&E-stained tissue cores. [PDF]

J Pathol
Abstract Pancreatic ductal adenocarcinoma (PDAC) subtyping typically relies on immunohistochemistry (IHC) staining for critical markers like HNF1A and KRT81, a labor‐intensive manual staining process that introduces variability. Virtual staining methods offer promising alternatives by generating synthetic IHC images from routine hematoxylin and eosin ...
Fischer M, Muckenhuber A, Peretzke R, Farah L, Ulrich C, Ziegler S, Schader P, Feineis L, Gao H, Xiao S, Götz M, Nolden M, Steiger K, Sieveke JT, Endrös L, Braren R, Kleesiek J, Schüffler P, Neher P, Maier-Hein K.   +19 more
europepmc   +2 more sources

CycleGAN-based Unpaired Speech Dereverberation

Interspeech 2022, 2022
Typically, neural network-based speech dereverberation models are trained on paired data, composed of a dry utterance and its corresponding reverberant utterance. The main limitation of this approach is that such models can only be trained on large amounts of data and a variety of room impulse responses when the data is synthetically reverberated ...
Muckenhirn, Hannah, Safin, Aleksandr, Erdogan, Hakan, Quitry, Felix de Chaumont, Tagliasacchi, Marco, Wisdom, Scott, Hershey, John R.   +6 more
openaire   +2 more sources

Generating Handwritten Chinese Characters Using CycleGAN [PDF]

2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 2018
Handwriting of Chinese has long been an important skill in East Asia. However, automatic generation of handwritten Chinese characters poses a great challenge due to the large number of characters. Various machine learning techniques have been used to recognize Chinese characters, but few works have studied the handwritten Chinese character generation ...
Chang, Bo, Zhang, Qiong, Pan, Shenyi, Meng, Lili   +3 more
openaire   +2 more sources