https://github.com/apple/ml-mgie
공식 코드Guiding Instruction-based Image Editing via Multimodal Large Language Models
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Guiding Instruction-based Image Editing via Multimodal Large Language Models
Style Generator Inversion for Image Enhancement and Animation
An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild
Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulation
Phenotype-preserving metric design for high-content image reconstruction by generative inpainting
FacialGAN: Style Transfer and Attribute Manipulation on Synthetic Faces
GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization
DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing
Image Manipulation Detection by Multi-View Multi-Scale Supervision
DreamSampler: Unifying Diffusion Sampling and Score Distillation for Image Manipulation
Image Shape Manipulation from a Single Augmented Training Sample
High Fidelity Visualization of What Your Self-Supervised Representation Knows About
Text as Neural Operator: Image Manipulation by Text Instruction
DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation
Region-Aware Diffusion for Zero-shot Text-driven Image Editing
Can We Find Neurons that Cause Unrealistic Images in Deep Generative Networks?
RG-Flow: A hierarchical and explainable flow model based on renormalization group and sparse prior
MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization
Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs
Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.