paper-with-me

Papers

GANs Conditioning Methods: A Survey

2024-08-28 · Anis Bourou, Valérie Mezger, Auguste Genovesio

In recent years, Generative Adversarial Networks (GANs) have seen significant advancements, leading to their widespread adoption across various fields. The original GAN architecture enables the generation of images without any specific control over the content, making it an unconditional generation process. However, many practical applications require precise control over the generated output, which has led to the development of conditional GANs (cGANs) that incorporate explicit conditioning to guide the generation process. cGANs extend the original framework by incorporating additional information (conditions), enabling the generation of samples that adhere to that specific criteria. Various conditioning methods have been proposed, each differing in how they integrate the conditioning information into both the generator and the discriminator networks. In this work, we review the conditioning methods proposed for GANs, exploring the characteristics of each method and highlighting their unique mechanisms and theoretical foundations. Furthermore, we conduct a comparative analysis of these methods, evaluating their performance on various image datasets. Through these analyses, we aim to provide insights into the strengths and limitations of various conditioning techniques, guiding future research and application in generative modeling.

📄 PDF Abstract BibTeX arXiv:2408.15640

Code (0)

등록된 구현이 없습니다.

Tasks

Survey

Similar Papers 제목 키워드 기반

Motion Generation: A Survey of Generative Approaches and Benchmarks

2025-07-07 · Aliasghar Khani, Arianna Rampini, Bruno Roy, Larasika Nadela 외

Motion generation, the task of synthesizing realistic motion sequences from various conditioning inputs, has become a central problem in computer vision, computer graphics, and robotics, with applications ranging from an…

Motion GenerationSurvey

Pixel-wise Conditioning of Generative Adversarial Networks

2019-11-02 · Cyprien Ruffino, Romain Hérault, Eric Laloy, Gilles Gasso

Generative Adversarial Networks (GANs) have proven successful for unsupervised image generation. Several works extended GANs to image inpainting by conditioning the generation with parts of the image one wants to reconst…

Image GenerationImage Inpainting

Collapse by Conditioning: Training Class-conditional GANs with Limited Data

2022-01-17 · ICLR 2022 4 · Mohamad Shahbazi, Martin Danelljan, Danda Pani Paudel, Luc van Gool

Class-conditioning offers a direct means to control a Generative Adversarial Network (GAN) based on a discrete input variable. While necessary in many applications, the additional information provided by the class labels…

Generative Adversarial Network

Precondition Layer and Its Use for GANs

2021-01-01 · Tiantian Fang, Alex Schwing, Ruoyu Sun

One of the major challenges when training generative adversarial nets (GANs) is instability. To address this instability spectral normalization (SN) is remarkably successful. However, SN-GAN still suffers from training…

GANStrument: Adversarial Instrument Sound Synthesis with Pitch-invariant Instance Conditioning

2022-11-10 · Gaku Narita, Junichi Shimizu, Taketo Akama

We propose GANStrument, a generative adversarial model for instrument sound synthesis. Given a one-shot sound as input, it is able to generate pitched instrument sounds that reflect the timbre of the input within an inte…

Diversity