Quality-Aware Unpaired Image-to-Image Translation
نویسندگان
چکیده
منابع مشابه
Supplementary Material for “Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervision”
Here we discuss the benefits of using non-parametric and domain-specific renderers, over learned decoders. Both the proposed model and CycleGAN [5] can be viewed as autoencoders: the input is first transformed into a target domain, and then transformed back to its original space. A parametric decoder could be more desirable, for the reason that we do not need to hand-engineer a mapping function...
متن کاملImproved Content Aware Image Retargeting Using Strip Partitioning
Based on rapid upsurge in the demand and usage of electronic media devices such as tablets, smart phones, laptops, personal computers, etc. and its different display specifications including the size and shapes, image retargeting became one of the key components of communication technology and internet. The existing techniques in image resizing cannot save the most valuable information of image...
متن کاملUnsupervised Image-to-Image Translation Networks
Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains. Since there exists an infinite set of joint distributions that can arrive the given marginal distributions, one could infer nothing about the joint distribution from the marginal distributions without additional assum...
متن کاملImage to Image Translation for Domain Adaptation
We propose a general framework for unsupervised domain adaptation, which allows deep neural networks trained on a source domain to be tested on a different target domain without requiring any training annotations in the target domain. This is achieved by adding extra networks and losses that help regularize the features extracted by the backbone encoder network. To this end we propose the novel...
متن کاملToward Multimodal Image-to-Image Translation
Many image-to-image translation problems are ambiguous, as a single input image may correspond to multiple possible outputs. In this work, we aim to model a distribution of possible outputs in a conditional generative modeling setting. The ambiguity of the mapping is distilled in a low-dimensional latent vector, which can be randomly sampled at test time. A generator learns to map the given inp...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Multimedia
سال: 2019
ISSN: 1520-9210,1941-0077
DOI: 10.1109/tmm.2019.2907052