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/s-sahoo/mulan
공식 코드https://github.com/sWizad/momentum-diffusion
공식 코드Diffusion Sampling with Momentum for Mitigating Divergence Artifacts
https://github.com/sachit-menon/generating-illustrated-instructions-reproduction
공식 코드https://github.com/sadil13/vln-ram
공식 코드https://github.com/safi842/Microstructure-GAN
공식 코드Establishing process-structure linkages using Generative Adversarial Networks
https://github.com/sagiebenaim/DistanceGAN
공식 코드https://github.com/sagiebenaim/OneShotTranslation
공식 코드https://github.com/sagiebenaim/gan_bound
공식 코드Estimating the Success of Unsupervised Image to Image Translation
https://github.com/sahilg06/EmoGen
공식 코드https://github.com/saic-mdal/CIPS
공식 코드Image Generators with Conditionally-Independent Pixel Synthesis
https://github.com/saic-mdal/HiDT
공식 코드https://github.com/saic-mdal/lama
공식 코드Resolution-robust Large Mask Inpainting with Fourier Convolutions
https://github.com/saic-violet/bilayer-model
공식 코드Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars
https://github.com/sail-sg/consistent3d
공식 코드https://github.com/sail-sg/fdm
공식 코드https://github.com/sail-sg/mdt
공식 코드MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer
https://github.com/sainzerjj/sferd
공식 코드Reducing Spatial Fitting Error in Distillation of Denoising Diffusion Models
https://github.com/sairajk/Thumbnail-Generation
공식 코드User Constrained Thumbnail Generation using Adaptive Convolutions
https://github.com/sairin1202/vp-csv
공식 코드Character-Centric Story Visualization via Visual Planning and Token Alignment
https://github.com/sais-fuxi/evalalign
공식 코드https://github.com/salanueva/sr4g
공식 코드https://github.com/salesforce/HIVE
공식 코드HIVE: Harnessing Human Feedback for Instructional Visual Editing
https://github.com/salesforce/doodl
공식 코드End-to-End Diffusion Latent Optimization Improves Classifier Guidance
https://github.com/salesforce/edict
공식 코드EDICT: Exact Diffusion Inversion via Coupled Transformations
https://github.com/salesforce/gluegen
공식 코드GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation
https://github.com/salesforce/lavis
공식 코드https://github.com/salesforce/unicontrol
공식 코드UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
https://github.com/samarthshukla/dcn
공식 코드Zero-Pair Image to Image Translation using Domain Conditional Normalization
https://github.com/samb-t/unleashing-transformers
공식 코드https://github.com/samgregoost/Rethinking-CGANs
공식 코드Rethinking conditional GAN training: An approach using geometrically structured latent manifolds
https://github.com/sandy-zeng/pcl
공식 코드Towards Effective Image Manipulation Detection with Proposal Contrastive Learning
https://github.com/sangwoomo/freezeD
공식 코드Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs
https://github.com/sangwoomo/instagan
공식 코드https://github.com/sangyun884/blur-diffusion
공식 코드Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis
https://github.com/sangyun884/rfpp
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.