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/snap-research/stable-flow

공식 코드

Stable Flow: Vital Layers for Training-Free Image Editing

https://github.com/sndnyang/Diffusion_ViT

공식 코드

Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model

https://github.com/sndnyang/GMMC

공식 코드

Generative Max-Mahalanobis Classifiers for Image Classification, Generation and More

https://github.com/sndnyang/mebm

공식 코드

M-EBM: Towards Understanding the Manifolds of Energy-Based Models

https://github.com/sndnyang/sadajem

공식 코드

Towards Bridging the Performance Gaps of Joint Energy-based Models

https://github.com/snu-drl/hrv

공식 코드

Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Models

https://github.com/snu-list/blindharmony

공식 코드

BlindHarmony: "Blind" Harmonization for MR Images via Flow model

https://github.com/snuvclab/chupa

공식 코드

Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models

https://github.com/socialabubi/iFakeFaceDB

공식 코드

GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection

https://github.com/sofeeyaj/poetry-in-pixels-coling2025

공식 코드

Poetry in Pixels: Prompt Tuning for Poem Image Generation via Diffusion Models

https://github.com/softrepa/SoftREPA

공식 코드

Aligning Text to Image in Diffusion Models is Easier Than You Think

https://github.com/somuchtome/faceswap

공식 코드

Face Swap via Diffusion Model

https://github.com/somuchtome/simac

공식 코드

SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models

https://github.com/songc42/feature-proliferation

공식 코드

Feature Proliferation -- the "Cancer" in StyleGAN and its Treatments

https://github.com/songluchuan/adasr-talkinghead

공식 코드

Adaptive Super Resolution For One-Shot Talking-Head Generation

https://github.com/songrise/Artist

공식 코드

DiffArtist: Towards Structure and Appearance Controllable Image Stylization

https://github.com/songrise/mllm4art

공식 코드

Multimodal LLMs Can Reason about Aesthetics in Zero-Shot

https://github.com/songweige/rich-text-to-image

공식 코드

Expressive Text-to-Image Generation with Rich Text

https://github.com/songyxing/idf-cr

공식 코드

IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Images

https://github.com/sonnguyen129/deep-feature-rotation

공식 코드

Deep Feature Rotation for Multimodal Image Style Transfer

https://github.com/sonny2020-c/rpfm-official-code

공식 코드

Real-Time Person Image Synthesis Using a Flow Matching Model

https://github.com/sony-si/MultiView-Img2Img

공식 코드

Multi-View Image-to-Image Translation Supervised by 3D Pose

https://github.com/sony/ctm

공식 코드

Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion

https://github.com/sony/pagoda

공식 코드

PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher

https://github.com/sony/san

공식 코드

SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer

https://github.com/sony/vct

공식 코드

Training Consistency Models with Variational Noise Coupling

https://github.com/soochan-lee/CN-DPM

공식 코드

A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning

https://github.com/soojunghong/image_inpainting_model_for_lane_geomery_discovery

공식 코드

Correcting Faulty Road Maps by Image Inpainting

https://github.com/soon-yau/kpe

공식 코드

KPE: Keypoint Pose Encoding for Transformer-based Image Generation

https://github.com/soon-yau/upgpt

공식 코드

UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer

https://github.com/soon-yau/visconet

공식 코드

ViscoNet: Bridging and Harmonizing Visual and Textual Conditioning for ControlNet

https://github.com/sophiajw/HistAuGAN

공식 코드

Structure-Preserving Multi-Domain Stain Color Augmentation using Style-Transfer with Disentangled Representations

https://github.com/sotiraslab/SC-VAE

공식 코드

SC-VAE: Sparse Coding-based Variational Autoencoder with Learned ISTA

https://github.com/sowwnn/KFusion-Dual-Domain-for-Speech-to-Landmarks

공식 코드

KAN-Based Fusion of Dual-Domain for Audio-Driven Facial Landmarks Generation

https://github.com/spaceml-org/expanding-sdo-capabilities

공식 코드

Using U-Nets to Create High-Fidelity Virtual Observations of the Solar Corona

https://github.com/sprintml/finetuning_var_dp

공식 코드

Implementing Adaptations for Vision AutoRegressive Model

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