https://github.com/minyoungg/pix2latent
Large Scale GAN Training for High Fidelity Natural Image Synthesis
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Image Generation (synthesis) is the task of generating new images from an existing dataset.
In this section, you can find state-of-the-art leaderboards for unconditional generation. For conditional generation, and other types of image generations, refer to the subtasks.
<span style="color:grey; opacity: 0.6">( Image credit: StyleGAN )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Large Scale GAN Training for High Fidelity Natural Image Synthesis
Geodesic Diffusion Models for Medical Image-to-Image Generation
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
Learning from Simulated and Unsupervised Images through Adversarial Training
Very Deep Convolutional Networks for Large-Scale Image Recognition
Very Deep Convolutional Networks for Large-Scale Image Recognition
Implicit Neural Representations with Periodic Activation Functions
Very Deep Convolutional Networks for Large-Scale Image Recognition
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
P+: Extended Textual Conditioning in Text-to-Image Generation
A Style-Based Generator Architecture for Generative Adversarial Networks
LEDITS++: Limitless Image Editing using Text-to-Image Models
Image-to-Image Translation with Conditional Adversarial Networks
StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Analyzing and Improving the Training Dynamics of Diffusion Models
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.