https://github.com/htyjers/dgts-inpainting
공식 코드Delving Globally into Texture and Structure for Image Inpainting
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/htyjers/strdiffusion
공식 코드Structure Matters: Tackling the Semantic Discrepancy in Diffusion Models for Image Inpainting
https://github.com/htzheng/CM-GAN-Inpainting
공식 코드CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Training
https://github.com/hu-zijing/b2-diffurl
공식 코드https://github.com/huage001/clear
공식 코드CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
https://github.com/huage001/dynast
공식 코드DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation
https://github.com/huage001/urae
공식 코드https://github.com/huangqiusheng/bridgegan
공식 코드https://github.com/huangwenwenlili/aca-crnet
공식 코드https://github.com/huanngzh/Parts2Whole
공식 코드From Parts to Whole: A Unified Reference Framework for Controllable Human Image Generation
https://github.com/huanpengchu/qncd
공식 코드https://github.com/huawei-lin/VTBench
공식 코드VTBench: Evaluating Visual Tokenizers for Autoregressive Image Generation
https://github.com/huawei-noah/noah-research/tree/master/TokenFusion
공식 코드https://github.com/hubert0527/infinityGAN
공식 코드https://github.com/huckiyang/EyeNet-GANs
공식 코드Synthesizing New Retinal Symptom Images by Multiple Generative Models
https://github.com/huggingface/amused
공식 코드https://github.com/huggingface/diffusers
공식 코드Improving Sample Quality of Diffusion Models Using Self-Attention Guidance
https://github.com/hui-po-wang/hijackgan
공식 코드https://github.com/huitailangyz/AFGAN
공식 코드Attributes Aware Face Generation with Generative Adversarial Networks
https://github.com/huitangtang/DADA-AAAI2020
공식 코드https://github.com/huiyegit/T2I_CL
공식 코드Improving Text-to-Image Synthesis Using Contrastive Learning
https://github.com/hukkelas/DeepPrivacy
공식 코드https://github.com/hulkima/pdrec
공식 코드https://github.com/humansensinglab/ITI-GEN
공식 코드https://github.com/humansensinglab/PATMAT
공식 코드PATMAT: Person Aware Tuning of Mask-Aware Transformer for Face Inpainting
https://github.com/hundredl/invdiff
공식 코드InvDiff: Invariant Guidance for Bias Mitigation in Diffusion Models
https://github.com/hunto/actgen
공식 코드https://github.com/hurunyi/videoshield
공식 코드VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking
https://github.com/huskynian/smo_egan_pytorch
공식 코드https://github.com/hust512/Tensor-GAN
공식 코드TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation
https://github.com/hustgetlijun/RCAN
공식 코드https://github.com/hustvl/LightningDiT
공식 코드Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
https://github.com/hustvl/controlar
공식 코드ControlAR: Controllable Image Generation with Autoregressive Models
https://github.com/hutaihang/atm
공식 코드Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing
https://github.com/hutaihang/faster-diffusion
공식 코드Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference
https://github.com/hutaihang/tome
공식 코드Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.