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/bayer-group/freggan
공식 코드fRegGAN with K-space Loss Regularization for Medical Image Translation
https://github.com/bbaaii/DreamDiffusion
공식 코드DreamDiffusion: Generating High-Quality Images from Brain EEG Signals
https://github.com/bbbbbbzhou/UCAN
공식 코드https://github.com/bcmi/ArtoPIH-Painterly-Image-Harmonization
공식 코드Painterly Image Harmonization by Learning from Painterly Objects
https://github.com/bcmi/Awesome-Image-Composition
공식 코드Making Images Real Again: A Comprehensive Survey on Deep Image Composition
https://github.com/bcmi/BargainNet-Image-Harmonization
공식 코드BargainNet: Background-Guided Domain Translation for Image Harmonization
https://github.com/bcmi/CDTNet-High-Resolution-Image-Harmonization
공식 코드High-Resolution Image Harmonization via Collaborative Dual Transformations
https://github.com/bcmi/DCI-VTON-Virtual-Try-On
공식 코드Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow
https://github.com/bcmi/DIRL
공식 코드https://github.com/bcmi/Image_Harmonization_Datasets
공식 코드Image Harmonization Dataset iHarmony4: HCOCO, HAdobe5k, HFlickr, and Hday2night
https://github.com/bcmi/Rendered_Image_Harmonization_Datasets
공식 코드https://github.com/bcmi/awesome-object-insertion
공식 코드Making Images Real Again: A Comprehensive Survey on Deep Image Composition
https://github.com/bcmi/controlcom-image-composition
공식 코드ControlCom: Controllable Image Composition using Diffusion Model
https://github.com/bcmi/deltagan-few-shot-image-generation
공식 코드DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta
https://github.com/bcmi/duconet-image-harmonization
공식 코드https://github.com/bcmi/image-harmonization-dataset-ccharmony
공식 코드https://github.com/bcmi/libcom
공식 코드Making Images Real Again: A Comprehensive Survey on Deep Image Composition
https://github.com/bcmi/madisnet-inharmonious-region-localization
공식 코드Inharmonious Region Localization by Magnifying Domain Discrepancy
https://github.com/bcmi/object-shadow-generation-dataset-desobav2
공식 코드https://github.com/bcmi/phdiffusion-painterly-image-harmonization
공식 코드https://github.com/bcmi/phdnet-painterly-image-harmonization
공식 코드https://github.com/bcmi/propih-painterly-image-harmonization
공식 코드Progressive Painterly Image Harmonization from Low-level Styles to High-level Styles
https://github.com/bcmi/syconet-adaptive-image-harmonization
공식 코드https://github.com/bdvllrs/bimgw
공식 코드Semi-supervised Multimodal Representation Learning through a Global Workspace
https://github.com/bebebe666/optimalsteps
공식 코드https://github.com/beichenzbc/long-clip
공식 코드https://github.com/benMen87/AppriximateConvolutionalSparseCoding
공식 코드https://github.com/benjaminjonghyun/rucgan
공식 코드https://github.com/bennytmt/riw
공식 코드A Somewhat Robust Image Watermark against Diffusion-based Editing Models
https://github.com/berenslab/disentangling-retinal-images
공식 코드Disentangling representations of retinal images with generative models
https://github.com/bertabescos/EmptyCities
공식 코드Empty Cities: Image Inpainting for a Dynamic-Object-Invariant Space
https://github.com/bes-dev/MobileStyleGAN.pytorch
공식 코드MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis
https://github.com/bes-dev/random_face
공식 코드MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis
https://github.com/bethgelab/frequency_determines_performance
공식 코드https://github.com/betterze/StyleAlign
공식 코드StyleAlign: Analysis and Applications of Aligned StyleGAN Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.