Papers with Code 아카이브
Conditional Image Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 11
- 보존된 평가 기록
- 75
Conditional image generation is the task of generating new images from a dataset conditional on their class.
<span style="color:grey; opacity: 0.6">( Image credit: PixelCNN++ )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Robust Conditional Generative Adversarial Networks
Self-Attention Generative Adversarial Networks
Text to Image Synthesis Using Generative Adversarial Networks
A Variational U-Net for Conditional Appearance and Shape Generation
Image Generation and Translation with Disentangled Representations
BRUNO: A Deep Recurrent Model for Exchangeable Data
cGANs with Projection Discriminator
Semi-supervised FusedGAN for Conditional Image Generation
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
Class-Splitting Generative Adversarial Networks
Improved ArtGAN for Conditional Synthesis of Natural Image and Artwork
GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data
Improved Training of Wasserstein GANs
GP-GAN: Towards Realistic High-Resolution Image Blending
Parallel Multiscale Autoregressive Density Estimation
LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation
ArtGAN: Artwork Synthesis with Conditional Categorical GANs
Calibrating Energy-based Generative Adversarial Networks
Stacked Generative Adversarial Networks
Invertible Conditional GANs for image editing
Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning
Conditional Image Synthesis With Auxiliary Classifier GANs
DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation
Conditional Image Generation with PixelCNN Decoders
Improved Techniques for Training GANs
Pixel-Level Domain Transfer
Attribute2Image: Conditional Image Generation from Visual Attributes
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.