Papers with Code 아카이브
Image Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/xt4d/sparsegnv
공식 코드SparseGNV: Generating Novel Views of Indoor Scenes with Sparse Input Views
https://github.com/xtudbxk/frecas
공식 코드FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling
https://github.com/xu-shitong/diffusion-image-captioning
공식 코드CLIP-Diffusion-LM: Apply Diffusion Model on Image Captioning
https://github.com/xuanqing94/AdvGAN
공식 코드https://github.com/xuanqing94/RobGAN
공식 코드https://github.com/xudonmao/RegCGAN
공식 코드Unpaired Multi-Domain Image Generation via Regularized Conditional GANs
https://github.com/xudonmao/pairedit
공식 코드PairEdit: Learning Semantic Variations for Exemplar-based Image Editing
https://github.com/xuehy/depthInpainting
공식 코드Depth Image Inpainting: Improving Low Rank Matrix Completion with Low Gradient Regularization
https://github.com/xuekt98/bbdm
공식 코드BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models
https://github.com/xuesong39/dac
공식 코드Doubly Abductive Counterfactual Inference for Text-based Image Editing
https://github.com/xufangchn/glf-cr
공식 코드https://github.com/xugao97/AttentionDistillation
공식 코드Attention Distillation: A Unified Approach to Visual Characteristics Transfer
https://github.com/xunhuang1995/SGAN
공식 코드https://github.com/xuqianren/semantic-guided-multi-mask-image-harmonization
공식 코드https://github.com/xuwangyin/at-ebms
공식 코드https://github.com/xuyanwu/SIDDMs-UFOGen
공식 코드UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs
https://github.com/xxxiaol/spatial-commonsense
공식 코드Things not Written in Text: Exploring Spatial Commonsense from Visual Signals
https://github.com/xyfjason/ctrlora
공식 코드CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation
https://github.com/xyfjason/hcl
공식 코드Hierarchical Contrastive Learning for Pattern-Generalizable Image Corruption Detection
https://github.com/xypeng9903/ncvsd
공식 코드https://github.com/xyzhouo/casd
공식 코드Cross Attention Based Style Distribution for Controllable Person Image Synthesis
https://github.com/xzhe-vision/personamagic
공식 코드PersonaMagic: Stage-Regulated High-Fidelity Face Customization with Tandem Equilibrium
https://github.com/xzlcan/cusconcept
공식 코드CusConcept: Customized Visual Concept Decomposition with Diffusion Models
https://github.com/yahyadogan72/iterative_facial_image_inpainting
공식 코드Iterative Facial Image Inpainting Based on an Encoder-Generator Architecture
https://github.com/yair-schiff/stochastic-orders-icmn
공식 코드https://github.com/yairshp/SISO
공식 코드Single Image Iterative Subject-driven Generation and Editing
https://github.com/yamand16/ear2face
공식 코드https://github.com/yandex-research/adaptive-diffusion
공식 코드https://github.com/yandex-research/dvar
공식 코드Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics
https://github.com/yandex-research/navigan
공식 코드Navigating the GAN Parameter Space for Semantic Image Editing
https://github.com/yandex-research/text-to-img-hypernymy
공식 코드Hypernymy Understanding Evaluation of Text-to-Image Models via WordNet Hierarchy
https://github.com/yang-song/score_flow
공식 코드https://github.com/yang-song/score_sde
공식 코드Score-Based Generative Modeling through Stochastic Differential Equations
https://github.com/yanghb22-fdu/3dstyle-diffusion-official
공식 코드3DStyle-Diffusion: Pursuing Fine-grained Text-driven 3D Stylization with 2D Diffusion Models
https://github.com/yanghb22-fdu/hi3d-official
공식 코드Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.