https://github.com/toshas/torch-fidelity
Improved Precision and Recall Metric for Assessing Generative Models
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.
Improved Precision and Recall Metric for Assessing Generative Models
Improved Techniques for Training Score-Based Generative Models
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
The relativistic discriminator: a key element missing from standard GAN
Very Deep Convolutional Networks for Large-Scale Image Recognition
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World
Guiding Instruction-based Image Editing via Multimodal Large Language Models
Indoor Depth Completion with Boundary Consistency and Self-Attention
Cycle-Consistent Generative Rendering for 2D-3D Modality Translation
FaceForensics++: Learning to Detect Manipulated Facial Images
Incorporating long-range consistency in CNN-based texture generation
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Learning to generate line drawings that convey geometry and semantics
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
Very Deep Convolutional Networks for Large-Scale Image Recognition
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Image-to-Image Translation with Conditional Adversarial Networks
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.