Statements (118)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:Model
gptkb:television_channel |
| gptkbp:bfsLayer |
4
|
| gptkbp:bfsParent |
gptkb:Cycle_GAN
|
| gptkbp:allows |
requires large datasets
may produce artifacts not suitable for unpaired image translation sensitive to training data quality |
| gptkbp:application |
semantic segmentation
image synthesis style transfer photo enhancement |
| gptkbp:applies_to |
image synthesis
|
| gptkbp:architectural_style |
gptkb:Alumni_Association
|
| gptkbp:based_on |
deep neural networks
image translation conditional GA Ns |
| gptkbp:developed_by |
gptkb:Phillip_Isola
|
| gptkbp:features |
gptkb:musician
gptkb:Photographer augmented reality autonomous driving real-time processing image editing unsupervised learning data augmentation image classification interactive applications object detection transfer learning facial recognition artistic applications image segmentation image generation scene understanding text-to-image synthesis video generation image compression image restoration image retrieval domain adaptation image stitching semi-supervised learning image captioning image denoising image super-resolution image blending image inpainting realistic image generation 3 D modeling image colorization content-aware image editing animation generation conditional image generation image morphing multi-modal outputs pixel-level translation |
| gptkbp:has_programs |
gptkb:musician
gptkb:Photographer autonomous driving art generation |
| gptkbp:has_variants |
gptkb:pix2pix_HD
gptkb:multi-domain_pix2pix gptkb:pix2pix++ pix2pix for video |
| https://www.w3.org/2000/01/rdf-schema#label |
pix2pix
|
| gptkbp:input_output |
paired images
translated images |
| gptkbp:inspired_by |
gptkb:pix2pix_HD
|
| gptkbp:is_a_framework_for |
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch |
| gptkbp:is_challenged_by |
newer models
adversarial attacks data scarcity computational limitations |
| gptkbp:is_documented_in |
research papers
tutorials online courses technical blogs |
| gptkbp:is_evaluated_by |
user studies
quantitative metrics PSNR qualitative assessments benchmark datasets SSIM |
| gptkbp:is_implemented_in |
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch |
| gptkbp:is_part_of |
computer vision
deep learning |
| gptkbp:is_popular_in |
gptkb:academic_circles
art communities tech industry |
| gptkbp:is_related_to |
gptkb:Artificial_Intelligence
gptkb:software_framework image processing |
| gptkbp:is_supported_by |
community contributions
open-source projects academic collaborations industry partnerships |
| gptkbp:is_used_for |
image editing
image enhancement style transfer image-to-image translation |
| gptkbp:is_used_in |
gptkb:film_production_company
gptkb:Research_Institute |
| gptkbp:losses |
L1 loss
|
| gptkbp:published_by |
gptkb:2016
|
| gptkbp:related_to |
gptkb:viewpoint
gptkb:Deep_Learning gptkb:Cycle_GAN gptkb:Style_GAN Generative Adversarial Networks (GA Ns) |
| gptkbp:resolution |
variable
|
| gptkbp:successor |
gptkb:Star_GAN
gptkb:pix2pix_HD gptkb:Cycle_GAN |
| gptkbp:training |
large datasets
|
| gptkbp:uses |
conditional Generative Adversarial Networks (c GA Ns)
|