https://github.com/vkinakh/InfoSCC-GAN
공식 코드Information-theoretic stochastic contrastive conditional GAN: InfoSCC-GAN
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.
Information-theoretic stochastic contrastive conditional GAN: InfoSCC-GAN
Sketch-guided Image Inpainting with Partial Discrete Diffusion Process
Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models
Implicit Neural Representations with Periodic Activation Functions
Guided Image-to-Image Translation with Bi-Directional Feature Transformation
Diversified in-domain synthesis with efficient fine-tuning for few-shot classification
Megapixel Image Generation with Step-Unrolled Denoising Autoencoders
Apply Hierarchical-Chain-of-Generation to Complex Attributes Text-to-3D Generation
SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow
Harmfully Manipulated Images Matter in Multimodal Misinformation Detection
Guaranteed Tensor Recovery Fused Low-rankness and Smoothness
Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing
DiffSketching: Sketch Control Image Synthesis with Diffusion Models
Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion
VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models
SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing
PhenDiff: Revealing Subtle Phenotypes with Diffusion Models in Real Images
Generative AI for Medical Imaging: extending the MONAI Framework
Learning to Adapt Structured Output Space for Semantic Segmentation
SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
Image Inpainting with Edge-guided Learnable Bidirectional Attention Maps
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.