Results 31 to 40 of about 5,457 (203)
CoRR, 2017 Face-off is an interesting case of style transfer where the facial expressions and attributes of one person could be fully transformed to another face. We are interested in the unsupervised training process which only requires two sequences of unaligned video frames from each person and learns what shared attributes to extract automatically.
Xiaohan Jin, Ye Qi, Shangxuan Wu
openaire +2 more sources
Database to train the Polarimetric CycleGAN
, 2021 Database to train the polarimetric CycleGAN, article in ...
Rachel Blin
core +1 more source
CycleGAN Variants for Industrial Defect Data Augmentation [PDF]
ITM Web of ConferencesIndustrial visual inspection is constrained by scarce labeled defect samples and complex surface patterns in bearings, steel, and ICs, significantly hindering deep learning detection models.
Xu Xiaoyu
doaj +1 more source
Scientific Reports, 2022 The heterogeneity of MRI is one of the major reasons for decreased performance of a radiomics model on external validation, limiting the model’s generalizability and clinical application.
Yae Won Park +8 more
doaj +1 more source
Image Colorization using CycleGAN with semantic and spatial rationality
, 2023 The goal of image colorization is to make the generated color images closely approximate the color layout of the real color images. However, most of the existing methods do not consider the semantic and spatial rationality of the generated images, and ...
Li, Bin +7 more
core +1 more source
Uncertainty-aware Generalized Adaptive CycleGAN
CoRR, 2021 13 pages, 9 ...
Uddeshya Upadhyay +2 more
openaire +3 more sources
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023 Supervised pansharpening methods require the ground truth, which is generally unavailable. Therefore, the popularity of unsupervised pansharpening methods has increased.
Wenxiu Diao +3 more
doaj +1 more source
Unpaired Underwater Image Enhancement Based on CycleGAN
, 2021 Underwater image enhancement recovers degraded underwater images to produce corresponding clear images. Image enhancement methods based on deep learning usually use paired data to train the model, while such paired data, e.g., the degraded images and the
Congying Li +4 more
core +1 more source
Research on the Style of Art Works based on Deep Learning
Journal of Advanced Transportation, 2022 In view of the unsatisfactory effect and major limitations of the style transfer of art works, this paper takes Chinese ink painting for the research subject.
Shulin Liu
doaj +1 more source
Improving de novo Molecule Generation by Embedding LSTM and Attention Mechanism in CycleGAN
Frontiers in Genetics, 2021 The application of deep learning in the field of drug discovery brings the development and expansion of molecular generative models along with new challenges in this field.
Feng Wang +6 more
doaj +1 more source