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/zalandoresearch/psgan
공식 코드https://github.com/zchoi/glscl
공식 코드Text-Video Retrieval with Global-Local Semantic Consistent Learning
https://github.com/zdxdsw/skewed_relations_t2i
공식 코드Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation
https://github.com/zeconloss/zecon
공식 코드Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer
https://github.com/zengbohan0217/FNeVR
공식 코드https://github.com/zengbohan0217/cmvdm
공식 코드https://github.com/zengbohan0217/fadm
공식 코드https://github.com/zengbohan0217/ipdreamer
공식 코드IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Prompts
https://github.com/zengjianhao/cat-dm
공식 코드CAT-DM: Controllable Accelerated Virtual Try-on with Diffusion Model
https://github.com/zengxianyu/crfill
공식 코드CR-Fill: Generative Image Inpainting with Auxiliary Contexutal Reconstruction
https://github.com/zes0v0inn/dwt_eeg_reconstruction
공식 코드Category-aware EEG image generation based on wavelet transform and contrast semantic loss
https://github.com/zeyuwang-zju/diffx
공식 코드https://github.com/zfw-cv/angiodiff
공식 코드https://github.com/zgj77/fsacdm
공식 코드https://github.com/zh460045050/vqgan-lc
공식 코드Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%
https://github.com/zhaisf/clid
공식 코드Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
https://github.com/zhang-lingyun/ConceptReplacer
공식 코드Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization
https://github.com/zhang-zx/AVID
공식 코드https://github.com/zhang-zx/sine
공식 코드SINE: SINgle Image Editing with Text-to-Image Diffusion Models
https://github.com/zhang0jhon/diffusion-4k
공식 코드Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models
https://github.com/zhangce01/degf
공식 코드https://github.com/zhangchenxu528/FACIAL
공식 코드FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute Learning
https://github.com/zhangguiwei610/v2flow
공식 코드https://github.com/zhangqianhui/3DSGAN
공식 코드3D-Aware Semantic-Guided Generative Model for Human Synthesis
https://github.com/zhangqianhui/SGGAN-tensorflow
공식 코드Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation
https://github.com/zhangqianhui/Sawn
공식 코드Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization
https://github.com/zhangqianhui/Sparsely-Grouped-GAN
공식 코드Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation
https://github.com/zhangqianhui/gazeanimationv2
공식 코드Unsupervised High-Resolution Portrait Gaze Correction and Animation
https://github.com/zhangqianhui/tt-gnerf
공식 코드https://github.com/zhangshy1019/composeanyone
공식 코드ComposeAnyone: Controllable Layout-to-Human Generation with Decoupled Multimodal Conditions
https://github.com/zhangxiaoyu11/omitrans
공식 코드OmiTrans: generative adversarial networks based omics-to-omics translation framework
https://github.com/zhangxulu1996/gal4personalization
공식 코드Generative Active Learning for Image Synthesis Personalization
https://github.com/zhangzc21/petsgan
공식 코드https://github.com/zhangzjn/emov2
공식 코드https://github.com/zhaolingao/rebel
공식 코드REBEL: Reinforcement Learning via Regressing Relative Rewards
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.