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/matt-bendel/rcgan

공식 코드

A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems

https://github.com/matteo-bastico/mi-seg

공식 코드

A Simple and Robust Framework for Cross-Modality Medical Image Segmentation applied to Vision Transformers

https://github.com/matteomaspero/overview_sct

공식 코드

Deep learning-based synthetic-CT generation in radiotherapy and PET: a review

https://github.com/max-liu-112/STGAN-WO

공식 코드

Towards Disentangling Latent Space for Unsupervised Semantic Face Editing

https://github.com/maxwellyaoni/chain

공식 코드

CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization

https://github.com/mayuelala/followyourpose

공식 코드

Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos

https://github.com/maziao/t2i-eval

공식 코드

Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark

https://github.com/mazurowski-lab/RaD

공식 코드

Fréchet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging Datasets

https://github.com/mazurowski-lab/medical-image-similarity-metrics

공식 코드

Fréchet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging Datasets

https://github.com/mazurowski-lab/segmentation-guided-diffusion

공식 코드

Anatomically-Controllable Medical Image Generation with Segmentation-Guided Diffusion Models

https://github.com/mbanani/novelviewpoints

공식 코드

Novel Object Viewpoint Estimation through Reconstruction Alignment

https://github.com/mbaradad/learning_with_noise

공식 코드

Learning to See by Looking at Noise

https://github.com/mc-e/dragondiffusion

공식 코드

DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing

https://github.com/mcahny/Deep-Video-Inpainting

공식 코드

Deep Video Inpainting

https://github.com/mcg-nju/bivdiff

공식 코드

BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models

https://github.com/mcg-nju/dmm

공식 코드

DMM: Building a Versatile Image Generation Model via Distillation-Based Model Merging

https://github.com/mcgill-nlp/diffusion-itm

공식 코드

Are Diffusion Models Vision-And-Language Reasoners?

https://github.com/mchong6/GANsNRoses

공식 코드

GANs N' Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!)

https://github.com/mchong6/SOAT

공식 코드

StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGAN

https://github.com/mdanyalmalik/chest-xray-synthesis

공식 코드

Evaluating the feasibility of using Generative Models to generate Chest X-Ray Data

https://github.com/mdhosen/mask-face-inpainting-using-residual-attention-unet

공식 코드

Masked Face Inpainting Through Residual Attention UNet

https://github.com/meclabtuda/med-nca

공식 코드

Med-NCA: Robust and Lightweight Segmentation with Neural Cellular Automata

https://github.com/megvii-research/MM2022-ViCoPerceptualHeadGeneration

공식 코드

Perceptual Conversational Head Generation with Regularized Driver and Enhanced Renderer

https://github.com/megvii-research/genegan

공식 코드

GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data

https://github.com/megvii-research/realflow

공식 코드

RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos

https://github.com/meituan-automl/visionllama

공식 코드

VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks

https://github.com/mengcye/LAION-SG

공식 코드

LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations

https://github.com/mengdanzhu/cross-modal-rag

공식 코드

Cross-modal RAG: Sub-dimensional Retrieval-Augmented Text-to-Image Generation

https://github.com/mengweiren/segmentation-renormalized-harmonization

공식 코드

Segmentation-Renormalized Deep Feature Modulation for Unpaired Image Harmonization

https://github.com/merlresearch/SteeredDiffusion

공식 코드

Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis

https://github.com/meteahishali/ada-net

공식 코드

ADA-Net: Attention-Guided Domain Adaptation Network with Contrastive Learning for Standing Dead Tree Segmentation Using Aerial Imagery

https://github.com/meteahishali/r2c-gan

공식 코드

R2C-GAN: Restore-to-Classify Generative Adversarial Networks for Blind X-Ray Restoration and COVID-19 Classification

https://github.com/meteoswiss/ldcast

공식 코드

Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification

https://github.com/mever-team/rine

공식 코드

Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection

https://github.com/mever-team/sidbench

공식 코드

SIDBench: A Python Framework for Reliably Assessing Synthetic Image Detection Methods

https://github.com/mezzelfo/MotionCraft

공식 코드

MotionCraft: Physics-based Zero-Shot Video Generation

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