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/avivga/style-image-prior
공식 코드Style Generator Inversion for Image Enhancement and Animation
https://github.com/avivga/zerodim
공식 코드An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild
https://github.com/avm-debatr/bagganhq
공식 코드Self-Supervised One-Shot Learning for Automatic Segmentation of StyleGAN Images
https://github.com/avm-debatr/ganecdotes
공식 코드Self-Supervised One-Shot Learning for Automatic Segmentation of StyleGAN Images
https://github.com/avra98/optimal-eye-surgeon
공식 코드Optimal Eye Surgeon: Finding Image Priors through Sparse Generators at Initialization
https://github.com/awesomelemon/hyfree-s3
공식 코드https://github.com/awesomelemon/pbt-nas
공식 코드https://github.com/awsaf49/artifact
공식 코드https://github.com/ayaanzhaque/EC-GAN
공식 코드EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs
https://github.com/ayanglab/cs2
공식 코드https://github.com/ayberkydn/stadv-torch
공식 코드Adversarial Image Generation by Spatial Transformation in Perceptual Colorspaces
https://github.com/aymenmir1/pix2surf
공식 코드Learning to Transfer Texture from Clothing Images to 3D Humans
https://github.com/aysanaghazadeh/CAP
공식 코드https://github.com/azadis/SB-GAN
공식 코드https://github.com/azadlab/FExGAN
공식 코드https://github.com/azadlab/FExGAN-Meta
공식 코드https://github.com/b-faye/prior-knowledge-norm
공식 코드Enhancing Neural Network Representations with Prior Knowledge-Based Normalization
https://github.com/baaivision/GeoDream
공식 코드GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation
https://github.com/baaivision/See3D
공식 코드You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale
https://github.com/baaivision/emu
공식 코드https://github.com/baaivision/nova
공식 코드https://github.com/baaivision/uni3d
공식 코드GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation
https://github.com/babahui/fine-grained-appearance-transfer
공식 코드https://github.com/babahui/progressive-text-to-image
공식 코드Progressive Text-to-Image Diffusion with Soft Latent Direction
https://github.com/bahjat-kawar/enhancing-diffusion-robust
공식 코드Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance
https://github.com/baidu/AdvBox
공식 코드A Tour of Convolutional Networks Guided by Linear Interpreters
https://github.com/ballerin/v1diffusion
공식 코드Geometry of the Visual Cortex with Applications to Image Inpainting and Enhancement
https://github.com/bansal-vansh/rectified-flow
공식 코드On the Wasserstein Convergence and Straightness of Rectified Flow
https://github.com/baofff/U-ViT
공식 코드https://github.com/barisgecer/TBGAN
공식 코드Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks
https://github.com/barisgecer/facegan
공식 코드https://github.com/basiralab/L2S-KDnet
공식 코드Inter-Domain Alignment for Predicting High-Resolution Brain Networks Using Teacher-Student Learning
https://github.com/batmanlab/ha-gan
공식 코드Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN
https://github.com/batmanlab/medsyn
공식 코드MedSyn: Text-guided Anatomy-aware Synthesis of High-Fidelity 3D CT Images
https://github.com/batmanlab/mspc
공식 코드Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.