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/koushiksrivats/robust-concept-erasing

공식 코드

STEREO: Towards Adversarially Robust Concept Erasing from Text-to-Image Generation Models

https://github.com/kpandey008/DiffuseVAE

공식 코드

DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents

https://github.com/kregmi/cross-view-image-synthesis

공식 코드

Cross-View Image Synthesis using Conditional GANs

https://github.com/krennic999/STAR

공식 코드

STAR: Scale-wise Text-to-image generation via Auto-Regressive representations

https://github.com/kristian10007/convgen

공식 코드

ConvGeN: Convex space learning improves deep-generative oversampling for tabular imbalanced classification on smaller datasets

https://github.com/kritiksoman/GIMP-ML

공식 코드

GIMP-ML: Python Plugins for using Computer Vision Models in GIMP

https://github.com/kschwethelm/hyperboliccv

공식 코드

Fully Hyperbolic Convolutional Neural Networks for Computer Vision

https://github.com/kshitij79/CS-7476-Improvements-in-Diffusion-Model

공식 코드

Enhancing Conditional Image Generation with Explainable Latent Space Manipulation

https://github.com/ku-milab/idenbat

공식 코드

IdenBAT: Disentangled Representation Learning for Identity-Preserved Brain Age Transformation

https://github.com/kuai-lab/sound-guided-semantic-image-manipulation

공식 코드

Sound-Guided Semantic Image Manipulation

https://github.com/kuleshov-group/discrete-diffusion-guidance

공식 코드

Simple Guidance Mechanisms for Discrete Diffusion Models

https://github.com/kumapowerliu/ffclip

공식 코드

One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations

https://github.com/kunheek/style-aware-discriminator

공식 코드

A Style-aware Discriminator for Controllable Image Translation

https://github.com/kunncheng/dit-sr

공식 코드

Effective Diffusion Transformer Architecture for Image Super-Resolution

https://github.com/kvablack/ddpo-pytorch

공식 코드

Training Diffusion Models with Reinforcement Learning

https://github.com/kwanyun/FFaceNeRF

공식 코드

FFaceNeRF: Few-shot Face Editing in Neural Radiance Fields

https://github.com/kwanyun/LeGO_code

공식 코드

LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example

https://github.com/kwonminki/Asyrp_official

공식 코드

Diffusion Models already have a Semantic Latent Space

https://github.com/kwotsin/mimicry

공식 코드

InfoMax-GAN: Improved Adversarial Image Generation via Information Maximization and Contrastive Learning

https://github.com/kxh001/info-decomp

공식 코드

Interpretable Diffusion via Information Decomposition

https://github.com/kxh001/itdiffusion

공식 코드

Information-Theoretic Diffusion

https://github.com/kynkaat/guidance-interval

공식 코드

Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models

https://github.com/kynkaat/improved-precision-and-recall-metric

공식 코드

Improved Precision and Recall Metric for Assessing Generative Models

https://github.com/kyungsu-lee-ksl/ash

공식 코드

Stochastic Adaptive Activation Function

https://github.com/l-yezhu/cdcd

공식 코드

Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation

https://github.com/labforcomputationalvision/local-probability-models-of-images

공식 코드

Learning multi-scale local conditional probability models of images

https://github.com/labhai-dev/Cyclic-2.5D-Perceptual-Loss

공식 코드

Cyclic 2.5D Perceptual Loss for Cross-Modal 3D Medical Image Synthesis: T1w MRI to Tau PET

https://github.com/labshuhanggu/perldiff

공식 코드

PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Models

https://github.com/lakonik/gmflow

공식 코드

Gaussian Mixture Flow Matching Models

https://github.com/lalithbharadwajbaru/wavelet-clip

공식 코드

Wavelet-Driven Generalizable Framework for Deepfake Face Forgery Detection

https://github.com/lamm-mit/llm-finetuning

공식 코드

Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities

https://github.com/lanl/blackout-diffusion

공식 코드

Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces

https://github.com/lanyu0303/geogpt4v_project

공식 코드

GeoGPT4V: Towards Geometric Multi-modal Large Language Models with Geometric Image Generation

https://github.com/lapid92/gd-vdm

공식 코드

GD-VDM: Generated Depth for better Diffusion-based Video Generation

https://github.com/large-scale-kim/EDM-AOT

공식 코드

Improving Diffusion-Based Generative Models via Approximated Optimal Transport

https://github.com/lattas/avatarme

공식 코드

AvatarMe: Realistically Renderable 3D Facial Reconstruction "in-the-wild"

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