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/jasonfu1998/diffpad

공식 코드

DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination

https://github.com/jasontslxd/pqwgan

공식 코드

Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation

https://github.com/jayLEE0301/vq_bet_official

공식 코드

Behavior Generation with Latent Actions

https://github.com/jbrenig/rescdc

공식 코드

Higher fidelity perceptual image and video compression with a latent conditioned residual denoising diffusion model

https://github.com/jchemseddine/conditional_wasserstein_distances

공식 코드

Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching

https://github.com/jcreinhold/intensity-normalization

공식 코드

Evaluating the Impact of Intensity Normalization on MR Image Synthesis

https://github.com/jcy132/Hneg_SRC

공식 코드

Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks

https://github.com/jdeschena/ddpm-zero-shot-interpolation

공식 코드

Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations

https://github.com/jeffhernandez1995/GenLlaVA

공식 코드

Generative Visual Instruction Tuning

https://github.com/jegzheng/truncated-diffusion-probabilistic-models

공식 코드

Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders

https://github.com/jenine-321/mfclip

공식 코드

MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection

https://github.com/jeremiastraub/diffusion

공식 코드

Representation Learning with Diffusion Models

https://github.com/jesse-merhi/CNN-TRAJGAN

공식 코드

Synthetic Trajectory Generation Through Convolutional Neural Networks

https://github.com/jessyblues/Causal-Longitudinal-Image-Synthesis

공식 코드

Longitudinal Causal Image Synthesis

https://github.com/jesusgf96/broad-unet

공식 코드

Broad-UNet: Multi-scale feature learning for nowcasting tasks

https://github.com/jgkwak95/surf-gan

공식 코드

Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis

https://github.com/jhoffman/cycada_release

공식 코드

CyCADA: Cycle-Consistent Adversarial Domain Adaptation

https://github.com/jhonatanoliveira/dcspns

공식 코드

Deep Generalized Convolutional Sum-Product Networks

https://github.com/jhonve/dcl-depthsynthesis

공식 코드

DCL: Differential Contrastive Learning for Geometry-Aware Depth Synthesis

https://github.com/jhw2000/jarnet

공식 코드

Deep Linear Array Pushbroom Image Restoration: A Degradation Pipeline and Jitter-Aware Restoration Network

https://github.com/jiachenlei/maskdm

공식 코드

Masked Diffusion Models Are Fast Distribution Learners

https://github.com/jiadingcn/geminifusion

공식 코드

GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer

https://github.com/jiangjiaxiu/mc-2

공식 코드

MC$^2$: Multi-concept Guidance for Customized Multi-concept Generation

https://github.com/jianningli/voxel_rearrangement

공식 코드

Learning to Rearrange Voxels in Binary Segmentation Masks for Smooth Manifold Triangulation

https://github.com/jianqingzheng/def_diff_rec

공식 코드

Deformation-Recovery Diffusion Model (DRDM): Instance Deformation for Image Manipulation and Synthesis

https://github.com/jiaosiyu1999/FlexVAR

공식 코드

FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction

https://github.com/jiarenchang/facecycle

공식 코드

Learning Facial Representations from the Cycle-consistency of Face

https://github.com/jiashunwang/Neural-Pose-Transfer

공식 코드

Neural Pose Transfer by Spatially Adaptive Instance Normalization

https://github.com/jiayuanwang-jw/adc-cyclegan

공식 코드

An Attentive-based Generative Model for Medical Image Synthesis

https://github.com/jiayuanwang-jw/dc-cyclegan

공식 코드

DC-cycleGAN: Bidirectional CT-to-MR Synthesis from Unpaired Data

https://github.com/jiayuyang/consistnet

공식 코드

ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion

https://github.com/jimmy-academia/lasgsa

공식 코드

Attack as the Best Defense: Nullifying Image-to-image Translation GANs via Limit-aware Adversarial Attack

https://github.com/jinc7461/ADG

공식 코드

Angle Domain Guidance: Latent Diffusion Requires Rotation Rather Than Extrapolation

https://github.com/jinchengzhanggg/proffusion

공식 코드

Mamba-Diffusion Model with Learnable Wavelet for Controllable Symbolic Music Generation

https://github.com/jindongjiang/latent-slot-diffusion

공식 코드

Object-Centric Slot Diffusion

https://github.com/jingjingchen777/CFGR

공식 코드

Coarse-to-Fine Gaze Redirection with Numerical and Pictorial Guidance

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