paper-with-me

Papers

Exploring the Capability of Text-to-Image Diffusion Models with Structural Edge Guidance for Multi-Spectral Satellite Image Inpainting

2023-11-06 · Mikolaj Czerkawski, Christos Tachtatzis

The letter investigates the utility of text-to-image inpainting models for satellite image data. Two technical challenges of injecting structural guiding signals into the generative process as well as translating the inpainted RGB pixels to a wider set of MSI bands are addressed by introducing a novel inpainting framework based on StableDiffusion and ControlNet as well as a novel method for RGB-to-MSI translation. The results on a wider set of data suggest that the inpainting synthesized via StableDiffusion suffers from undesired artifacts and that a simple alternative of self-supervised internal inpainting achieves a higher quality of synthesis.

📄 PDF Abstract BibTeX arXiv:2311.03008

Code (0)

등록된 구현이 없습니다.

Tasks

Image InpaintingTranslation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.

Similar Papers 제목 키워드 기반

Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement

2024-02-15 · Tao Yang, Cuiling Lan, Yan Lu, Nanning Zheng

Disentangled representation learning strives to extract the intrinsic factors within observed data. Factorizing these representations in an unsupervised manner is notably challenging and usually requires tailored loss fu…

DisentanglementImage ReconstructionInductive BiasRepresentation Learning

IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models

2023-08-13 · Hu Ye, Jun Zhang, Sibo Liu, Xiao Han 외

Recent years have witnessed the strong power of large text-to-image diffusion models for the impressive generative capability to create high-fidelity images. However, it is very tricky to generate desired images using on…

Diffusion Personalization Tuning FreeImage GenerationPersonalized Image GenerationPrompt Engineering

Unveiling Structural Memorization: Structural Membership Inference Attack for Text-to-Image Diffusion Models

2024-07-18 · Qiao Li, Xiaomeng Fu, Xi Wang, Jin Liu 외

With the rapid advancements of large-scale text-to-image diffusion models, various practical applications have emerged, bringing significant convenience to society. However, model developers may misuse the unauthorized d…

Inference AttackMembership Inference AttackMemorization

Recognition-Guided Diffusion Model for Scene Text Image Super-Resolution

2023-11-22 · Yuxuan Zhou, Liangcai Gao, Zhi Tang, Baole Wei

Scene Text Image Super-Resolution (STISR) aims to enhance the resolution and legibility of text within low-resolution (LR) images, consequently elevating recognition accuracy in Scene Text Recognition (STR). Previous met…

DenoisingDiversityImage Super-ResolutionScene Text Recognition+1

DIFF-NST: Diffusion Interleaving For deFormable Neural Style Transfer

2023-07-09 · Dan Ruta, Gemma Canet Tarrés, Andrew Gilbert, Eli Shechtman 외

Neural Style Transfer (NST) is the field of study applying neural techniques to modify the artistic appearance of a content image to match the style of a reference style image. Traditionally, NST methods have focused on …

Image GenerationStyle Transfer