https://github.com/1202kbs/gctm
공식 코드Generalized Consistency Trajectory Models for Image Manipulation
Papers with Code 아카이브
Image Manipulation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 2
Image Manipulation is the process of altering or transforming an existing image to achieve a desired effect or to modify its content. This can involve various techniques and tools to enhance, modify, or create images based on specific requirements.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/99eren99/dirfiaf
공식 코드https://github.com/99eren99/dis25k
공식 코드https://github.com/AKASH2907/Forgery-Classification-via-Domain-Adaptation
공식 코드Syn2Real: Forgery Classification via Unsupervised Domain Adaptation
https://github.com/AaltoVision/balanced-pioneer
공식 코드Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders
https://github.com/CV-Lehigh/Bias_IMD
공식 코드https://github.com/Championchess/DLGAN
공식 코드DLGAN: Disentangling Label-Specific Fine-Grained Features for Image Manipulation
https://github.com/EricGzq/AMTENnet
공식 코드Fake face detection via adaptive manipulation traces extraction network
https://github.com/EvgenyKashin/stylegan2-distillation
공식 코드https://github.com/Fantasy-Studio/Paint-by-Example
공식 코드Paint by Example: Exemplar-based Image Editing with Diffusion Models
https://github.com/InterDigitalInc/HRFAE
공식 코드https://github.com/KelestZ/Latent2im
공식 코드Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation
https://github.com/LeiaLi/SRDiff
공식 코드SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models
https://github.com/MAPS-research/Ditail
공식 코드Diffusion Cocktail: Mixing Domain-Specific Diffusion Models for Diversified Image Generations
https://github.com/MohitLamba94/Iterative-Pooling
공식 코드https://github.com/NetEase-GameAI/clipvg
공식 코드CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphics
https://github.com/PruneTruong/DenseMatching
공식 코드Learning Accurate Dense Correspondences and When to Trust Them
https://github.com/PruneTruong/PDCNet
공식 코드Learning Accurate Dense Correspondences and When to Trust Them
https://github.com/RaoulusHPC/KiMont_StyleGAN3D
공식 코드https://github.com/SijieSong/person_generation_spt
공식 코드Unsupervised Person Image Generation with Semantic Parsing Transformation
https://github.com/Tengfei-Wang/HFGI
공식 코드https://github.com/UT-Mao/Initial-Noise-Editing
공식 코드Guided Image Synthesis via Initial Image Editing in Diffusion Model
https://github.com/VinAIResearch/HyperInverter
공식 코드HyperInverter: Improving StyleGAN Inversion via Hypernetwork
https://github.com/XingangPan/DragGAN
공식 코드Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
https://github.com/XingangPan/deep-generative-prior
공식 코드Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
https://github.com/Yan98/S2FGAN
공식 코드S2FGAN: Semantically Aware Interactive Sketch-to-Face Translation
https://github.com/Yikai-Wang/SeMani/tree/main/SeMani-Trans
공식 코드https://github.com/YooJiHyeong/SinIR
공식 코드SinIR: Efficient General Image Manipulation with Single Image Reconstruction
https://github.com/adobe-research/domain-expansion
공식 코드HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation
https://github.com/affromero/SMILE
공식 코드SMILE: Semantically-guided Multi-attribute Image and Layout Editing
https://github.com/ai-forever/kandinsky-3
공식 코드Kandinsky 3: Text-to-Image Synthesis for Multifunctional Generative Framework
https://github.com/ailab-cvc/seed-x
공식 코드SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing
https://github.com/allenai/embodied-clip
공식 코드https://github.com/aminkaramlou/qnlg
공식 코드https://github.com/andreas128/SRFlow
공식 코드SRFlow: Learning the Super-Resolution Space with Normalizing Flow
https://github.com/andysonys/selective-diffusion-distillation
공식 코드Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.