https://github.com/MLI-lab/overparameterized_convolutional_generators
공식 코드Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators
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/MLO-lab/Disentangling_Mean_Embeddings
공식 코드Disentangling Mean Embeddings for Better Diagnostics of Image Generators
https://github.com/MRUIL/WDNet
공식 코드WDNet: Watermark-Decomposition Network for Visible Watermark Removal
https://github.com/MRzzm/DINet
공식 코드DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Video
https://github.com/MS-Diffusion/MS-Diffusion
공식 코드MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance
https://github.com/MSoumm/FaVFA
공식 코드Fairer Analysis and Demographically Balanced Face Generation for Fairer Face Verification
https://github.com/MartinBuessemeyer/Artistic-Texture-Control
공식 코드Controlling Geometric Abstraction and Texture for Artistic Images
https://github.com/Maryeon/InvMM
공식 코드An Inversion-based Measure of Memorization for Diffusion Models
https://github.com/MarziEd/SubSpace-Capsule-Network
공식 코드https://github.com/MaxReimann/WISE-Editing
공식 코드https://github.com/Medabid1/I2I-LR
공식 코드https://github.com/MenghaoGuo/-EANet
공식 코드Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
https://github.com/MenghaoGuo/Awesome-Vision-Attentions
공식 코드https://github.com/MengyingLei/GLSKF
공식 코드https://github.com/Meta-Portrait/MetaPortrait
공식 코드MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation
https://github.com/MhLiao/SynthText3D
공식 코드SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds
https://github.com/MiaoyunZhao/GANTransferLimitedData
공식 코드On Leveraging Pretrained GANs for Generation with Limited Data
https://github.com/MichaelArbel/GeneralizedEBM
공식 코드https://github.com/MichaelArbel/Scaled-MMD-GAN
공식 코드https://github.com/MichalGeyer/plug-and-play
공식 코드Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
https://github.com/Microsoft/TRELLIS
공식 코드Structured 3D Latents for Scalable and Versatile 3D Generation
https://github.com/MinkaiXu/Discriminator-Contrastive-Divergence
공식 코드https://github.com/MiriUll/Image-Generation-for-Accessible-Communication
공식 코드Images Speak Volumes: User-Centric Assessment of Image Generation for Accessible Communication
https://github.com/MoPl90/image_translation
공식 코드Image Translation for Medical Image Generation -- Ischemic Stroke Lesions
https://github.com/MoeinSorkhei/glow2
공식 코드Full-Glow: Fully conditional Glow for more realistic image generation
https://github.com/MohammadRSalmanpour/MRI-to-US-Translation_MICCAI
공식 코드https://github.com/MohitLamba94/Iterative-Pooling
공식 코드https://github.com/MohitShridhar/genima
공식 코드https://github.com/MonoFormer/MonoFormer
공식 코드MonoFormer: One Transformer for Both Diffusion and Autoregression
https://github.com/Mosasaur5526/BCM-iCT-torch
공식 코드https://github.com/MrRezaeiUofT/IDFF
공식 코드Implicit Dynamical Flow Fusion (IDFF) for Generative Modeling
https://github.com/MrTornado24/FENeRF
공식 코드https://github.com/Mukosame/AODA
공식 코드Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis
https://github.com/MunchkinChen/FADING
공식 코드https://github.com/NVIDIA/Megatron-LM
공식 코드ZeRO: Memory Optimizations Toward Training Trillion Parameter Models
https://github.com/NVIDIA/partialconv
공식 코드Image Inpainting for Irregular Holes Using Partial Convolutions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.