https://github.com/thudm/visualglm-6b
CogView: Mastering Text-to-Image Generation via Transformers
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.
CogView: Mastering Text-to-Image Generation via Transformers
Very Deep Convolutional Networks for Large-Scale Image Recognition
Domain Adaptive Faster R-CNN for Object Detection in the Wild
Image-to-Image Translation with Conditional Adversarial Networks
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
In-N-Out: Towards Good Initialization for Inpainting and Outpainting
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Unsupervised Meta-learning of Figure-Ground Segmentation via Imitating Visual Effects
Unsupervised Meta-learning of Figure-Ground Segmentation via Imitating Visual Effects
Semantic Image Synthesis with Spatially-Adaptive Normalization
Image Restoration by Iterative Denoising and Backward Projections
The Surprising Effectiveness of Linear Unsupervised Image-to-Image Translation
Implicit Neural Representations with Periodic Activation Functions
Image-to-Image Translation with Conditional Adversarial Networks
Image Inpainting via Generative Multi-column Convolutional Neural Networks
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation
DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Unsupervised Learning of Object Landmarks through Conditional Image Generation
Image-to-Image Translation with Conditional Adversarial Networks
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
SinGAN: Learning a Generative Model from a Single Natural Image
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.