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/archinetai/audio-diffusion-pytorch
공식 코드Moûsai: Text-to-Music Generation with Long-Context Latent Diffusion
https://github.com/architect-road/icongan
공식 코드Design What You Desire: Icon Generation from Orthogonal Application and Theme Labels
https://github.com/ardasahiner/ProCoGAN
공식 코드Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions
https://github.com/aria-zhangjl/e3-facenet
공식 코드https://github.com/ariel415el/Efficient-GPNN
공식 코드Generating natural images with direct Patch Distributions Matching
https://github.com/ariel415el/gpdm
공식 코드Generating natural images with direct Patch Distributions Matching
https://github.com/arnabk001/Pose-Invariant-Person-Re-Identification-using-Robust-Pose-Transfromation-GAN
공식 코드Pose Invariant Person Re-Identification using Robust Pose-transformation GAN
https://github.com/aroitberg/sims4action
공식 코드https://github.com/arraiyopensource/kornia
공식 코드https://github.com/arthur-qiu/stylefacev
공식 코드StyleFaceV: Face Video Generation via Decomposing and Recomposing Pretrained StyleGAN3
https://github.com/arunsehrawat/interferometric-neural-networks
공식 코드https://github.com/aryamohan23/eht-gans
공식 코드https://github.com/aryan-garg/styledcgan
공식 코드https://github.com/aryan-jadon/synthetic-data-generation-and-evaluation-using-reasoning-models
공식 코드https://github.com/ashual/scene_generation
공식 코드Specifying Object Attributes and Relations in Interactive Scene Generation
https://github.com/askerlee/lapstyle
공식 코드https://github.com/asperti/Embedding-in-Diffusion-Models
공식 코드https://github.com/astatine-213-tian/text-to-artistic-image-generation
공식 코드https://github.com/astra-vision/guideddisent
공식 코드Physics-informed Guided Disentanglement in Generative Networks
https://github.com/astrazeneca/mcpl
공식 코드https://github.com/atenrev/diffusion_continual_learning
공식 코드Continual Learning of Diffusion Models with Generative Distillation
https://github.com/atenrev/difussion_continual_learning
공식 코드Continual Learning of Diffusion Models with Generative Distillation
https://github.com/atonderski/lidarclip
공식 코드https://github.com/autodeskailab/clip-forge
공식 코드https://github.com/autonomousvision/controllable_image_synthesis
공식 코드Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis
https://github.com/autonomousvision/counterfactual_generative_networks
공식 코드https://github.com/autonomousvision/giraffe
공식 코드GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields
https://github.com/autonomousvision/graf
공식 코드GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
https://github.com/autonomousvision/projected_gan
공식 코드https://github.com/autonomousvision/stylegan-t
공식 코드StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
https://github.com/autonomousvision/stylegan_xl
공식 코드https://github.com/autonomousvision/voxgraf
공식 코드VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
https://github.com/avdpro/ai2apps
공식 코드AI2Agent: An End-to-End Framework for Deploying AI Projects as Autonomous Agents
https://github.com/avinashpaliwal/ReShader
공식 코드ReShader: View-Dependent Highlights for Single Image View-Synthesis
https://github.com/avisekiit/TCSVT-LightWeight-CNNs
공식 코드Lightweight Modules for Efficient Deep Learning based Image Restoration
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.