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/Tengfei-Wang/HFGI

공식 코드

High-Fidelity GAN Inversion for Image Attribute Editing

https://github.com/Tengfei-Wang/external-internal-inpainting

공식 코드

Image Inpainting with External-internal Learning and Monochromic Bottleneck

https://github.com/Texaser/MTN

공식 코드

Progressive Text-to-3D Generation for Automatic 3D Prototyping

https://github.com/The-FinAI/FinTagging

공식 코드

FinTagging: An LLM-ready Benchmark for Extracting and Structuring Financial Information

https://github.com/ThisisBillhe/ZipAR

공식 코드

ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality

https://github.com/TimeLighter/pytorch-sym-parameter

공식 코드

Sym-parameterized Dynamic Inference for Mixed-Domain Image Translation

https://github.com/TimoBolkart/voca

공식 코드

Capture, Learning, and Synthesis of 3D Speaking Styles

https://github.com/TingHLiao/ELDA

공식 코드

ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDA

https://github.com/Tinysqua/UWAT-GAN

공식 코드

UWAT-GAN: Fundus Fluorescein Angiography Synthesis via Ultra-wide-angle Transformation Multi-scale GAN

https://github.com/TitorX/GVCFDiffusion

공식 코드

Guided and Variance-Corrected Fusion with One-shot Style Alignment for Large-Content Image Generation

https://github.com/ToniCreswell/attribute-cVAEGAN

공식 코드

Adversarial Information Factorization

https://github.com/TonyLianLong/LLM-groundedDiffusion

공식 코드

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models

https://github.com/ToyotaCRDL/Visual-Concept-Blending

공식 코드

Zero-Shot Visual Concept Blending Without Text Guidance

https://github.com/TrinitialChan/DifFSS

공식 코드

DifFSS: Diffusion Model for Few-Shot Semantic Segmentation

https://github.com/Trustworthy-Engineered-Autonomy-Lab/generalizable-image-repair

공식 코드

Generalizable Image Repair for Robust Visual Autonomous Racing

https://github.com/TsaftarisCollaboratory/CSDisentanglement_Metrics_Library

공식 코드

Measuring the Biases and Effectiveness of Content-Style Disentanglement

https://github.com/UBC-Computer-Vision-Group/attribute-guided-image-generation-from-layout

공식 코드

Attribute-guided image generation from layout

https://github.com/UBCDingXin/DDRE_Sampling_GANs

공식 코드

Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space with Softplus Loss

https://github.com/UBCDingXin/cDR-RS

공식 코드

Efficient Subsampling of Realistic Images From GANs Conditional on a Class or a Continuous Variable

https://github.com/UBCDingXin/improved_CcGAN

공식 코드

Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input Mechanisms

https://github.com/USTC-JialunPeng/Diverse-Structure-Inpainting

공식 코드

Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE

https://github.com/UT-Mao/Initial-Noise-Construction

공식 코드

The Lottery Ticket Hypothesis in Denoising: Towards Semantic-Driven Initialization

https://github.com/UT-Mao/Initial-Noise-Editing

공식 코드

Guided Image Synthesis via Initial Image Editing in Diffusion Model

https://github.com/VARGPT-family/VARGPT

공식 코드

VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model

https://github.com/VAST-AI-Research/TripoSG

공식 코드

TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

https://github.com/VCG-team/DiffSegmenter

공식 코드

Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter

https://github.com/VITA-Group/BlackBoxGANCollapse

공식 코드

Black-Box Diagnosis and Calibration on GAN Intra-Mode Collapse: A Pilot Study

https://github.com/VITA-Group/GAN-LTH

공식 코드

GANs Can Play Lottery Tickets Too

https://github.com/VITA-Group/Sandwich-Batch-Normalization

공식 코드

Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity

https://github.com/VITA-Group/TransGAN

공식 코드

TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up

https://github.com/VLL-HD/FrEIA

공식 코드

Guided Image Generation with Conditional Invertible Neural Networks

https://github.com/VLL-HD/conditional_INNs

공식 코드

Conditional Invertible Neural Networks for Diverse Image-to-Image Translation

https://github.com/VMBoehm/PAE

공식 코드

Probabilistic Autoencoder

https://github.com/VRI-UFPR/IDA

공식 코드

IDA: Improved Data Augmentation Applied to Salient Object Detection

https://github.com/VSainteuf/utae-paps

공식 코드

Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks

https://github.com/Vadori/CytoArk

공식 코드

HistoSmith: Single-Stage Histology Image-Label Generation via Conditional Latent Diffusion for Enhanced Cell Segmentation and Classification

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