https://github.com/soran-ghaderi/torchebm
Generative Modeling by Estimating Gradients of the Data Distribution
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.
Generative Modeling by Estimating Gradients of the Data Distribution
The relativistic discriminator: a key element missing from standard GAN
Image-to-Image Translation with Conditional Adversarial Networks
Very Deep Convolutional Networks for Large-Scale Image Recognition
Very Deep Convolutional Networks for Large-Scale Image Recognition
Very Deep Convolutional Networks for Large-Scale Image Recognition
High-Resolution Image Synthesis with Latent Diffusion Models
Diffusion Model Alignment Using Direct Preference Optimization
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Very Deep Convolutional Networks for Large-Scale Image Recognition
Progressive Distillation for Fast Sampling of Diffusion Models
Image-to-Image Translation with Conditional Adversarial Networks
Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
When Does Perceptual Alignment Benefit Vision Representations?
High-Resolution Image Synthesis with Latent Diffusion Models
ControlVAE: Tuning, Analytical Properties, and Performance Analysis
Direct Ascent Synthesis: Revealing Hidden Generative Capabilities in Discriminative Models
Very Deep Convolutional Networks for Large-Scale Image Recognition
SinGAN: Learning a Generative Model from a Single Natural Image
StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
Progressive Growing of GANs for Improved Quality, Stability, and Variation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.