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/jychoi118/ilvr_adm

공식 코드

ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models

https://github.com/jychoi118/toward_spatial_unbiased

공식 코드

Toward Spatially Unbiased Generative Models

https://github.com/k8xu/imageattribution

공식 코드

Detecting Origin Attribution for Text-to-Image Diffusion Models

https://github.com/ka-anderson/pge-reconstruction

공식 코드

Revealing Unintentional Information Leakage in Low-Dimensional Facial Portrait Representations

https://github.com/kahroba2000/biogan

공식 코드

BioGAN: An unpaired GAN-based image to image translation model for microbiological images

https://github.com/kaiizhang/mfa

공식 코드

Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation

https://github.com/kaiseem/dar-unet

공식 코드

CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation

https://github.com/kaist-cvml-lab/scribble-diffusion

공식 코드

Scribble-Guided Diffusion for Training-free Text-to-Image Generation

https://github.com/kaiyuesun98/t2i-personalization-with-ar

공식 코드

Personalized Text-to-Image Generation with Auto-Regressive Models

https://github.com/kakaobrain/magvlt

공식 코드

MAGVLT: Masked Generative Vision-and-Language Transformer

https://github.com/kakaobrain/rq-vae-transformer

공식 코드

Autoregressive Image Generation using Residual Quantization

https://github.com/kakashiz/nedb-net

공식 코드

Noise and Edge Based Dual Branch Image Manipulation Detection

https://github.com/kamata1729/FullySpikingVAE

공식 코드

Fully Spiking Variational Autoencoder

https://github.com/kamigaito/wikitig

공식 코드

Table and Image Generation for Investigating Knowledge of Entities in Pre-trained Vision and Language Models

https://github.com/kaminyou/urust

공식 코드

Ultra-high-resolution unpaired stain transformation via Kernelized Instance Normalization

https://github.com/kamwoh/chirpy3d

공식 코드

Chirpy3D: Creative Fine-grained 3D Object Fabrication via Part Sampling

https://github.com/kangyeolk/animeceleb

공식 코드

AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment

https://github.com/kangyeolk/paint-by-sketch

공식 코드

Reference-based Image Composition with Sketch via Structure-aware Diffusion Model

https://github.com/kantamasuki/rgdm

공식 코드

Generative diffusion model with inverse renormalization group flows

https://github.com/kapilw25/Evaluation_generated_images

공식 코드

Multimodal Benchmarking and Recommendation of Text-to-Image Generation Models

https://github.com/karenyyy/miccai2021_attributegan

공식 코드

A Multi-attribute Controllable Generative Model for Histopathology Image Synthesis

https://github.com/karrykkk/bayesdiff

공식 코드

BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference

https://github.com/katieluo88/staypositive

공식 코드

Stay Positive: Non-Negative Image Synthesis for Augmented Reality

https://github.com/kazuto1011/dusty-gan

공식 코드

Learning to Drop Points for LiDAR Scan Synthesis

https://github.com/kb824999404/HRIG

공식 코드

High-resolution Rainy Image Synthesis: Learning from Rendering

https://github.com/kdst-team/naturalinversion

공식 코드

NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistency

https://github.com/keeganhk/pointvst

공식 코드

PointVST: Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translation

https://github.com/keisuke-okb/class-conditioned-ODI-generator-pytorch

공식 코드

Omni-Directional Image Generation from Single Snapshot Image

https://github.com/ken-ouyang/PGMPI

공식 코드

Real-Time Neural Character Rendering with Pose-Guided Multiplane Images

https://github.com/kennymckormick/Triplet-Representation-of-human-Body

공식 코드

TRB: A Novel Triplet Representation for Understanding 2D Human Body

https://github.com/keqpan/udsr

공식 코드

Unpaired Depth Super-Resolution in the Wild

https://github.com/kevinhkhsu/DA_detection

공식 코드

Progressive Domain Adaptation for Object Detection

https://github.com/kevinhuangxf/fingerveinrecognition

공식 코드

Motion Transfer-Driven intra-class data augmentation for Finger Vein Recognition

https://github.com/kevinlight831/sage

공식 코드

SAGE: Exploring the Boundaries of Unsafe Concept Domain with Semantic-Augment Erasing

https://github.com/kevinrojas1499/diffuse-everything

공식 코드

Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces

https://github.com/kfirgoldberg/ConceptLab

공식 코드

ConceptLab: Creative Concept Generation using VLM-Guided Diffusion Prior Constraints

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