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/google/trax/blob/master/trax/models/research/hourglass.py

공식 코드

Hierarchical Transformers Are More Efficient Language Models

https://github.com/google/trax/tree/master/trax/models/reformer

공식 코드

Reformer: The Efficient Transformer

https://github.com/google/zoom-to-inpaint

공식 코드

Zoom-to-Inpaint: Image Inpainting with High-Frequency Details

https://github.com/gpt4vision/OvSGTR

공식 코드

Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention

https://github.com/gr8joo/IIAE

공식 코드

Variational Interaction Information Maximization for Cross-domain Disentanglement

https://github.com/grandpaxun242/adabldm

공식 코드

A Novel Approach to Industrial Defect Generation through Blended Latent Diffusion Model with Online Adaptation

https://github.com/greatx3/playable-game-generation

공식 코드

Playable Game Generation

https://github.com/grigorisg9gr/polynomial_nets

공식 코드

$Π-$nets: Deep Polynomial Neural Networks

https://github.com/grigorisg9gr/polynomial_nets_for_conditional_generation

공식 코드

CoPE: Conditional image generation using Polynomial Expansions

https://github.com/grigorisg9gr/rocgan

공식 코드

Robust Conditional Generative Adversarial Networks

https://github.com/grimalpaul/tiam

공식 코드

TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation

https://github.com/gsgen3d/gsgen

공식 코드

Text-to-3D using Gaussian Splatting

https://github.com/guanhaisu/obsd

공식 코드

Deciphering Oracle Bone Language with Diffusion Models

https://github.com/gudovskiy/odelt

공식 코드

$\textrm{ODE}_t \left(\textrm{ODE}_l \right)$: Shortcutting the Time and Length in Diffusion and Flow Models for Faster Sampling

https://github.com/guhuangai/ddm-public

공식 코드

Simultaneous Image-to-Zero and Zero-to-Noise: Diffusion Models with Analytical Image Attenuation

https://github.com/guicamargox/retamd

공식 코드

Robust deep learning for eye fundus images: Bridging real and synthetic data for enhancing generalization

https://github.com/guicamargox/synthetic-retina-amd

공식 코드

Robust deep learning for eye fundus images: Bridging real and synthetic data for enhancing generalization

https://github.com/guigzos/crossmodalgba

공식 코드

Cross-modal tumor segmentation using generative blending augmentation and self training

https://github.com/guillaumebrg/texture_generation

공식 코드

Incorporating long-range consistency in CNN-based texture generation

https://github.com/guillermogotre/cusp

공식 코드

Custom Structure Preservation in Face Aging

https://github.com/gulcinbaykal/DeshuffleGAN

공식 코드

DeshuffleGAN: A Self-Supervised GAN to Improve Structure Learning

https://github.com/gulnazaki/counterfactual-benchmark

공식 코드

Benchmarking Counterfactual Image Generation

https://github.com/guopeiming/E2E_PSDG

공식 코드

An End-to-End Model for Photo-Sharing Multi-modal Dialogue Generation

https://github.com/guoqiang-x-zhang/AidaOptimizer

공식 코드

A DNN Optimizer that Improves over AdaBelief by Suppression of the Adaptive Stepsize Range

https://github.com/guoqiang-zhang-x/BDIA

공식 코드

Exact Diffusion Inversion via Bi-directional Integration Approximation

https://github.com/guoqiushan/egc

공식 코드

EGC: Image Generation and Classification via a Diffusion Energy-Based Model

https://github.com/guoyaoshen/k-sapcecolddiffusion

공식 코드

Learning to Reconstruct Accelerated MRI Through K-space Cold Diffusion without Noise

https://github.com/guoyongcs/AEGAN

공식 코드

Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis

https://github.com/guthasaibharathchandra/MAP-GA

공식 코드

Inverse Problems with Diffusion Models: A MAP Estimation Perspective

https://github.com/guytevet/motion-diffusion-model

공식 코드

Human Motion Diffusion Model

https://github.com/guyyariv/AudioToken

공식 코드

AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation

https://github.com/guyyariv/vlmig

공식 코드

Improving Visual Commonsense in Language Models via Multiple Image Generation

https://github.com/gvisani/hpacker

공식 코드

H-Packer: Holographic Rotationally Equivariant Convolutional Neural Network for Protein Side-Chain Packing

https://github.com/gvogiatzis/trafficgen

공식 코드

Synthesizing Traffic Datasets using Graph Neural Networks

https://github.com/gwang-kim/diffusionclip

공식 코드

DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation

https://github.com/gyhandy/text2image-for-detection

공식 코드

Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentation

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