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/xcyan/eccv16_attr2img
Attribute2Image: Conditional Image Generation from Visual Attributes
https://github.com/xcyan/neurips18_hierchical_image_manipulation
Learning Hierarchical Semantic Image Manipulation through Structured Representations
https://github.com/xhlulu/arxiv-assistant
https://github.com/xhujoy/CycleGAN-tensorflow
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
https://github.com/xiandenis/iPERCore
Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis
https://github.com/xiaoboCASIA/SV-X-Softmax
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
https://github.com/xiaohangzhan/deocclusion
https://github.com/xiaohui9607/llm_layout_generator
https://github.com/xiaoiker/meta_dpm
https://github.com/xiaosheng-zhao/st4diffusion
https://github.com/xiaowillow/AdaptSegNet
Learning to Adapt Structured Output Space for Semantic Segmentation
https://github.com/xiaowillow/AdaptSegNet1
Learning to Adapt Structured Output Space for Semantic Segmentation
https://github.com/xiaoyu258/Inbetweening
https://github.com/xiaoyufenfei/LEDNet
https://github.com/xingchenzhao/Generating-Human-Skeletons-with-Mutual-Actions-WGAN-Pytorch
Image-to-Image Translation with Conditional Adversarial Networks
https://github.com/xingchenzhao/deep-learning-team-project
Image-to-Image Translation with Conditional Adversarial Networks
https://github.com/xinkuansong/modified-resnet-acc-0.9638-10.7M-parameters
https://github.com/xinshengwang/S2IGAN
https://github.com/xiongjiechen/ASWD
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
https://github.com/xirongc/watermark-audio-diffusion
TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets
https://github.com/xiuyu0000/new_papers_codes/tree/main/Pix2PixHD
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
https://github.com/xiuyu0000/papers_with_examples/tree/main/cancer_detection_demo
https://github.com/xiuyu0000/papers_with_examples/tree/main/cyclegan
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
https://github.com/xiuyu0000/papers_with_examples/tree/main/pix2pix
Image-to-Image Translation with Conditional Adversarial Networks
https://github.com/xiuyu0000/papers_with_examples/tree/main/stylegan2
A Style-Based Generator Architecture for Generative Adversarial Networks
https://github.com/xiuyu0000/tutorials/tree/main/resnet
https://github.com/xiuyu0000/vision/blob/main/mindvision/classification/models/resnet.py
https://github.com/xiuyu0000/vision/blob/main/mindvision/classification/models/vgg.py
Very Deep Convolutional Networks for Large-Scale Image Recognition
https://github.com/xiwei-cheng/chained_ld
Generative Modeling by Estimating Gradients of the Data Distribution
https://github.com/xkp793003821/PConv-Keras
Image Inpainting for Irregular Holes Using Partial Convolutions
https://github.com/xl402/performer
https://github.com/xlwan/KRnet
https://github.com/xmu-xiaoma666/External-Attention-pytorch
Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
https://github.com/xqding/RealNVP
https://github.com/xrenaa/StyleSpace-pytorch
StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.