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/xuanliu2000/vgcdm
Adding Conditional Control to Text-to-Image Diffusion Models
https://github.com/xuduo35/InstructPix2Pix
InstructPix2Pix: Learning to Follow Image Editing Instructions
https://github.com/xuduo35/MakeLongVideo
Make-A-Video: Text-to-Video Generation without Text-Video Data
https://github.com/xuduo35/UniTune
UniTune: Text-Driven Image Editing by Fine Tuning a Diffusion Model on a Single Image
https://github.com/xuefusiji/badrefsr
Learning Texture Transformer Network for Image Super-Resolution
https://github.com/xufanxiong/classification-of-caltech-256
https://github.com/xunings/styleganime2
https://github.com/xurongchao/mv-inpainting
https://github.com/xw-hu/Mask-ShadowGAN
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
https://github.com/xx88xx/stylegan2ky
https://github.com/xxlya/CycleGAN
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
https://github.com/xxxNARUTO228xxx/Neural-Style-Transfer-Gatys-LapStyle
https://github.com/xxxliu95/RA_FA_Cardiac
Disentangled Representation Learning in Cardiac Image Analysis
https://github.com/xypeng9903/k-diffusion-inverse-problems
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
https://github.com/xypu98/two-stage-HDR-video
A Two-stage Deep Network for High Dynamic Range Image Reconstruction
https://github.com/xyzforever/bevt
https://github.com/y0ast/Glow-PyTorch
https://github.com/yahoo/open_nsfw
https://github.com/yakhyo/EfficientNet-PyTorch
https://github.com/yakhyo/Fast-Neural-Style-Transfer
Instance Normalization: The Missing Ingredient for Fast Stylization
https://github.com/yakhyo/gaze-estimation
https://github.com/yakhyo/head-pose-estimation
https://github.com/yakhyo/retinaface-pytorch
https://github.com/yalharbi/StructuredNoiseInjection
Disentangled Image Generation Through Structured Noise Injection
https://github.com/yan-roo/FakeFace
A Style-Based Generator Architecture for Generative Adversarial Networks
https://github.com/yanfeng-yang-0316/cdcit
Score-Based Generative Modeling through Stochastic Differential Equations
https://github.com/yang-song/score_inverse_problems
Score-Based Generative Modeling through Stochastic Differential Equations
https://github.com/yang-song/score_sde_pytorch
Generative Modeling by Estimating Gradients of the Data Distribution
https://github.com/yangboz/TransferLearning4Dentist
Very Deep Convolutional Networks for Large-Scale Image Recognition
https://github.com/yangli-lab/artifact-eraser
https://github.com/yangorwell/NGPlus
https://github.com/yangyucheng000/CRA
Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting
https://github.com/yangyucheng000/CycleGan
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
https://github.com/yangyucheng000/ICT
High-Fidelity Pluralistic Image Completion with Transformers
https://github.com/yangyucheng000/MSpaper/tree/main/U-GAT-IT
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.