https://github.com/yehli/xmodaler
공식 코드Semantic-Conditional Diffusion Networks for Image Captioning
Papers with Code 아카이브
Image Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 23
- 평가표
- 93
- 보존된 평가 기록
- 870
Image Generation (synthesis) is the task of generating new images from an existing dataset.
- Unconditional generation refers to generating samples unconditionally from the dataset, i.e. $p(y)$
- Conditional image generation (subtask) refers to generating samples conditionally from the dataset, based on a label, i.e. $p(y|x)$.
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>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/yerfor/Real3DPortrait
공식 코드Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis
https://github.com/yeshaokai/Calibrator-Domain-Adaptation
공식 코드Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation
https://github.com/ygjwd12345/GLANet
공식 코드Global and Local Alignment Networks for Unpaired Image-to-Image Translation
https://github.com/yhZhai/WSCL
공식 코드Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning
https://github.com/yhlleo/DWC-GAN
공식 코드Describe What to Change: A Text-guided Unsupervised Image-to-Image Translation Approach
https://github.com/yhlleo/GMM-UNIT
공식 코드https://github.com/yhlleo/RG-UNIT
공식 코드Retrieval Guided Unsupervised Multi-domain Image-to-Image Translation
https://github.com/yhlleo/stylegan-mmuit
공식 코드ISF-GAN: An Implicit Style Function for High-Resolution Image-to-Image Translation
https://github.com/yhsong98/ct-us-i2i-translation
공식 코드https://github.com/yhyang-myron/sampart3d-website
공식 코드https://github.com/yhyun225/DiffuseHigh
공식 코드DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance
https://github.com/yifan123/flow_grpo
공식 코드https://github.com/yifei-liu-stat/pass
공식 코드Perturbation-Assisted Sample Synthesis: A Novel Approach for Uncertainty Quantification
https://github.com/yigitgunduc/tensor-to-image
공식 코드Tensor-to-Image: Image-to-Image Translation with Vision Transformers
https://github.com/yigitgunduc/vit-gan
공식 코드Vit-GAN: Image-to-image Translation with Vision Transformes and Conditional GANS
https://github.com/yikai-wang/asuka-misato
공식 코드https://github.com/yikai-wang/res
공식 코드https://github.com/yikai-wang/semani
공식 코드https://github.com/yikaiw/CEN
공식 코드https://github.com/yikaiw/TokenFusion
공식 코드https://github.com/yikaiw/vidu4d
공식 코드Video4DGen: Enhancing Video and 4D Generation through Mutual Optimization
https://github.com/yikang-li/PasteGAN
공식 코드PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph
https://github.com/yikidragon/dsffnet
공식 코드DSFFNet: Dual-Side Feature Fusion Network for 3D Pose Transfer
https://github.com/yilmazkorkmaz1/i2i-galip
공식 코드I2I-Galip: Unsupervised Medical Image Translation Using Generative Adversarial CLIP
https://github.com/yilundu/reduce_reuse_recycle
공식 코드Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC
https://github.com/yiminghh/hog-diff
공식 코드HOG-Diff: Higher-Order Guided Diffusion for Graph Generation
https://github.com/yingchen001/WaveFill
공식 코드WaveFill: A Wavelet-based Generation Network for Image Inpainting
https://github.com/yingchen001/cf-clip
공식 코드https://github.com/yinghdb/micgans
공식 코드Unsupervised Image Generation with Infinite Generative Adversarial Networks
https://github.com/yingkaid/jailfuzzer
공식 코드https://github.com/yingqichao/From-Image-to-Imuge-Immunized-Image-Generation
공식 코드https://github.com/yingqinghe/lvdm
공식 코드Latent Video Diffusion Models for High-Fidelity Long Video Generation
https://github.com/yingqinghe/scalecrafter
공식 코드ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models
https://github.com/yinyjin/dualanodiff
공식 코드DualAnoDiff: Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation
https://github.com/yinzhicun/metaf2n
공식 코드MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.