Generative Attribute Controller with Conditional Filtered Generative Adversarial Networks

By Takuhiro Kaneko, Kaoru Hiramatsu, Kunio Kashino. 2017

95 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition, Generative Models, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

In Generative Models

In Signal Processing

Citations in the corpus

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs (2017, background): “Compared to L1 loss, which often leads to blurry images [21, 22], the adversarial loss [16] has become a popular choice for many image-to-image tasks [10, 24, 25, 31, 40, 45, 53, 58, 64].”
Semantics Disentangling for Text-To-Image Generation (2019, background): “GAN-based algorithms show excellent performance in image generation [21, 1, 20, 25, 35, 2, 23].”
Spatially Controllable Image Synthesis with Internal Representation Collaging (2018, methodology): “Finally, by combining our methods with manifold projection [44], we can adopt the strategy similar to the ones taken by [44, 3, 18] and make spatial semantic manipulation of real images as well.”
Bidirectional Conditional Generative Adversarial Networks (2017, methodology): “data from complex distributions for a variety of applications such as image editing [23], image synthesis from text descriptions [24], image super-resolution [14], video summarization [17] and others [2,8,10,11,15,26,28,29,30, 32,34,35], with very promising results. The core methodology for modeling”
Diverse Image Synthesis From Semantic Layouts via Conditional IMLE (2018, methodology): “[16, 28, 30] explore conditioning on attributes that can be modified manually by the user at test time; these methods are not true multimodal methods because they require manual changes to the input (rather than just sampling from a fixed distribution) to generate a different image.”
Improving Consistency and Correctness of Sequence Inpainting using Semantically Guided Generative Adversarial Network (2017, methodology): “, have been used in [18] to interactively modify a given image.”
Applications of Generative Adversarial Networks (GANs): An Updated Review (2019, background): “Kaneko et al. [52] presented a generative attribute controller (GAC), a novel functionality for generating or editing an image while intuitively controlling large variations of an attribute.”
A Layer-Based Sequential Framework for Scene Generation with GANs (2019, background): “…have been proposed to control the generation process by conditioning on a class label (Odena, Olah, and Shlens 2017), an attribute vector (Kaneko, Hiramatsu, and Kashino 2017; Ding, Sricharan, and Chellappa 2018), a text description (Reed et al. 2016a; Johnson, Gupta, and Fei-Fei 2018),…”
AttGAN: Facial Attribute Editing by Only Changing What You Want (2017, methodology): “The solution used in this work is to maximize the mutual information between θ and the generated image xθ ∼ Gdec(Genc(x), θ ∗ b) in order to make them highly correlated [31], [33], i.”
FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification (2018, background): “GAN-based algorithms shows excellent performance in image generation [13, 14, 15, 16, 17].”