Papers with Code 아카이브

Image Generation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/tgisaturday/L-Verse

공식 코드

L-Verse: Bidirectional Generation Between Image and Text

https://github.com/tgxs002/hpsv2

공식 코드

Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis

https://github.com/thanhluantrinh/lddgan

공식 코드

Latent Denoising Diffusion GAN: Faster sampling, Higher image quality

https://github.com/thanos-db/pixelsmith

공식 코드

Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models

https://github.com/thended32/analyzingfeatureextractors

공식 코드

Analyzing the Feature Extractor Networks for Face Image Synthesis

https://github.com/theroadqaq/predicting-distortion

공식 코드

Evaluating and Predicting Distorted Human Body Parts for Generated Images

https://github.com/thinkercache/stylegan2-ada-pytorch

공식 코드

High Fidelity Synthetic Face Generation for Rosacea Skin Condition from Limited Data

https://github.com/thisisbillhe/efficientdm

공식 코드

EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models

https://github.com/thisisbillhe/nar

공식 코드

Neighboring Autoregressive Modeling for Efficient Visual Generation

https://github.com/thmoa/tex2shape

공식 코드

Tex2Shape: Detailed Full Human Body Geometry From a Single Image

https://github.com/thomaskerdreux/pdm_sar_insar_generation

공식 코드

Diffusion Models for Interferometric Satellite Aperture Radar

https://github.com/threestudio-project/threestudio

공식 코드

Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation

https://github.com/thu-cvml/texturediffusion

공식 코드

TextureDiffusion: Target Prompt Disentangled Editing for Various Texture Transfer

https://github.com/thu-ml/SageAttention

공식 코드

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

https://github.com/thu-ml/cep-energy-guided-diffusion

공식 코드

Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning

https://github.com/thu-ml/dpm-solver-v3

공식 코드

DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics

https://github.com/thu-ml/i-dode

공식 코드

Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs

https://github.com/thu-ml/unidiffuser

공식 코드

One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale

https://github.com/thu-ml/vflow

공식 코드

VFlow: More Expressive Generative Flows with Variational Data Augmentation

https://github.com/thu-spmi/Inclusive-NRF

공식 코드

Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly Detection

https://github.com/thuan2412/joint-covariate-alignment-and-concept-alignment-for-domain-generalization

공식 코드

Joint covariate-alignment and concept-alignment: a framework for domain generalization

https://github.com/thudm/cogview2

공식 코드

CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers

https://github.com/thudm/imagereward

공식 코드

ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation

https://github.com/thudm/inf-dit

공식 코드

Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer

https://github.com/thundercondor/imageclefmed-medvqa-gi-2024-mmcp-team

공식 코드

Prompt to Polyp: Medical Text-Conditioned Image Synthesis with Diffusion Models

https://github.com/thunguyenphuoc/HoloGAN

공식 코드

HoloGAN: Unsupervised learning of 3D representations from natural images

https://github.com/thunlp/acdit

공식 코드

ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer

https://github.com/tiago939/feature_aligment

공식 코드

Feature Alignment as a Generative Process

https://github.com/tiago939/feature_alignment

공식 코드

Feature Alignment as a Generative Process

https://github.com/tiagocortinhal/titan-next

공식 코드

Depth- and Semantics-aware Multi-modal Domain Translation: Generating 3D Panoramic Color Images from LiDAR Point Clouds

https://github.com/tianhewu/visualquality-r1

공식 코드

VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank

https://github.com/tiankaihang/language-guided-animation

공식 코드

Language-Guided Face Animation by Recurrent StyleGAN-based Generator

https://github.com/tiankaihang/min-snr-diffusion-training

공식 코드

Efficient Diffusion Training via Min-SNR Weighting Strategy

https://github.com/tianweiy/DMD2

공식 코드

Improved Distribution Matching Distillation for Fast Image Synthesis

https://github.com/tianyi-lab/DisCL

공식 코드

Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion

https://github.com/tianyilt/textcengen_background_adapt

공식 코드

TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.