https://github.com/glovo/foodi-ml-dataset
공식 코드FooDI-ML: a large multi-language dataset of food, drinks and groceries images and descriptions
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/gmum/PALATE
공식 코드https://github.com/gnobitab/RectifiedFlow
공식 코드Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
https://github.com/gnobitab/fusedream
공식 코드FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization
https://github.com/gnobitab/instaflow
공식 코드InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
https://github.com/godisboy/DRPAN
공식 코드Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation
https://github.com/gogoduan/got-r1
공식 코드GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning
https://github.com/gohyojun15/SplatFlow
공식 코드SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis
https://github.com/gojasper/flash-diffusion
공식 코드Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation
https://github.com/gojasper/lbm
공식 코드LBM: Latent Bridge Matching for Fast Image-to-Image Translation
https://github.com/gol2022/impus
공식 코드IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models
https://github.com/google-deepmind/proactive_t2i_agents
공식 코드Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty
https://github.com/google-research-datasets/adversarial-nibbler
공식 코드https://github.com/google-research-datasets/visage
공식 코드ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation
https://github.com/google-research/big_vision
공식 코드https://github.com/google-research/generative_transfer
공식 코드https://github.com/google-research/google-research
공식 코드https://github.com/google-research/google-research/tree/master/autoregressive_diffusion
공식 코드https://github.com/google-research/google-research/tree/master/cmmd
공식 코드Rethinking FID: Towards a Better Evaluation Metric for Image Generation
https://github.com/google-research/google-research/tree/master/diffusion_distillation
공식 코드Progressive Distillation for Fast Sampling of Diffusion Models
https://github.com/google-research/google-research/tree/master/infinite_nature
공식 코드Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image
https://github.com/google-research/google-research/tree/master/robust_loss
공식 코드https://github.com/google-research/hit-gan
공식 코드https://github.com/google-research/maskgit
공식 코드https://github.com/google-research/masksketch
공식 코드MaskSketch: Unpaired Structure-guided Masked Image Generation
https://github.com/google-research/nested-transformer
공식 코드https://github.com/google-research/pix2seq
공식 코드Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
https://github.com/google-research/vdm
공식 코드https://github.com/google-research/xmcgan_image_generation
공식 코드Cross-Modal Contrastive Learning for Text-to-Image Generation
https://github.com/google/compare_gan
공식 코드https://github.com/google/imageinwords
공식 코드https://github.com/google/lecam-gan
공식 코드Regularizing Generative Adversarial Networks under Limited Data
https://github.com/google/localized-narratives
공식 코드https://github.com/google/prompt-to-prompt
공식 코드https://github.com/google/style-aligned
공식 코드https://github.com/google/tim-gan
공식 코드Text as Neural Operator: Image Manipulation by Text Instruction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.