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/valeoai/maskgit-pytorch
공식 코드A Pytorch Reproduction of Masked Generative Image Transformer
https://github.com/vamosc/caphuman
공식 코드https://github.com/vancyland/prompt-agnostic-adversarial-perturbation-for-customized-diffusion-models.github.io
공식 코드Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
https://github.com/vancyland/vancyland.github.io-project-PAP
공식 코드Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
https://github.com/vanderschaarlab/evaluating-generative-models
공식 코드https://github.com/vandriiashen/mc-scattering
공식 코드Quantifying the effect of X-ray scattering for data generation in real-time defect detection
https://github.com/vandriiashen/pod2settings
공식 코드X-ray Image Generation as a Method of Performance Prediction for Real-Time Inspection: a Case Study
https://github.com/vanshali/pathopolyp-diff
공식 코드https://github.com/vargpt-family/vargpt-v1.1
공식 코드https://github.com/vasatdan/wgain-inpaint
공식 코드Image Inpainting Using Wasserstein Generative Adversarial Imputation Network
https://github.com/vasily789/adaptive-weighted-gans
공식 코드Adaptive Weighted Discriminator for Training Generative Adversarial Networks
https://github.com/vast-ai-research/triposr
공식 코드https://github.com/vchitect/vbench
공식 코드VBench: Comprehensive Benchmark Suite for Video Generative Models
https://github.com/vdeborto/cdsb
공식 코드https://github.com/vectorspacelab/omnigen
공식 코드https://github.com/vectorspacelab/omnigen2
공식 코드https://github.com/vegb/inlg
공식 코드Visualize Before You Write: Imagination-Guided Open-Ended Text Generation
https://github.com/venturamor/cultext-2-i
공식 코드Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models
https://github.com/verazuo/prompt-stealing-attack
공식 코드Prompt Stealing Attacks Against Text-to-Image Generation Models
https://github.com/verlab/empowering-sign-language
공식 코드https://github.com/versusdebias/versusdebias
공식 코드https://github.com/vfcosta/clip-gan-es
공식 코드Exploring Generative Adversarial Networks for Text-to-Image Generation with Evolution Strategies
https://github.com/vglsd/AIM2020-Image-Inpainting-Challenge
공식 코드https://github.com/vglsd/OpenSESAME
공식 코드SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects
https://github.com/vglsd/scaleparty
공식 코드https://github.com/vicgalle/stable-diffusion-aesthetic-gradients
공식 코드Personalizing Text-to-Image Generation via Aesthetic Gradients
https://github.com/vickyFox/Region-wise-Inpainting
공식 코드Region-wise Generative Adversarial ImageInpainting for Large Missing Areas
https://github.com/vict0rsch/LiSS
공식 코드Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation
https://github.com/victoria-project/mam-e
공식 코드MAM-E: Mammographic synthetic image generation with diffusion models
https://github.com/videocrafter/talecrafter
공식 코드TaleCrafter: Interactive Story Visualization with Multiple Characters
https://github.com/viiika/Meissonic
공식 코드https://github.com/viiika/viewcontrol
공식 코드https://github.com/vikolss/DACS
공식 코드https://github.com/villawang/Neuro-AI-Interface
공식 코드Synthetic-Neuroscore: Using A Neuro-AI Interface for Evaluating Generative Adversarial Networks
https://github.com/vinairesearch/anti-dreambooth
공식 코드Anti-DreamBooth: Protecting users from personalized text-to-image synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.