paper-with-me

홈 › Papers

CC-Diff: Enhancing Contextual Coherence in Remote Sensing Image Synthesis

2024-12-11 · Mu Zhang, Yunfan Liu, Yue Liu, Hongtian Yu, Qixiang Ye

Accurately depicting real-world landscapes in remote sensing (RS) images requires precise alignment between objects and their environment. However, most existing synthesis methods for natural images prioritize foreground control, often reducing the background to plain textures. This neglects the interaction between foreground and background, which can lead to incoherence in RS scenarios. In this paper, we introduce CC-Diff, a Diffusion Model-based approach for RS image generation with enhanced Context Coherence. To capture spatial interdependence, we propose a sequential pipeline where background generation is conditioned on synthesized foreground instances. Distinct learnable queries are also employed to model both the complex background texture and its semantic relation to the foreground. Extensive experiments demonstrate that CC-Diff outperforms state-of-the-art methods in visual fidelity, semantic accuracy, and positional precision, excelling in both RS and natural image domains. CC-Diff also shows strong trainability, improving detection accuracy by 2.04 mAP on DOTA and 2.25 mAP on the COCO benchmark.

📄 PDF Abstract BibTeX arXiv:2412.08464

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

SFR-Net: Learning Scale-Frustum Representations for Ultra-Wide Area Remote Sensing Image Segmentation

2026-05-25 · Chuyu Zhong, Keyan Chen, Qinzhe Yang, Bowen Chen 외 arxiv

Pixel count and geographical coverage are two key characteristics of remote sensing images. Existing remote sensing image segmentation methods typically focus on images with either a small pixel count or a large pixel co…

Image Segmentation

ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG

2024-11-12 · Zilun Zhang, Haozhan Shen, Tiancheng Zhao, Zian Guan 외

Ultra High Resolution (UHR) remote sensing imagery (RSI) (e.g. 100,000 $\times$ 100,000 pixels or more) poses a significant challenge for current Remote Sensing Multimodal Large Language Models (RSMLLMs). If choose to re…

RAGRetrievalRetrieval-augmented Generation

C-SAW: Self-Supervised Prompt Learning for Image Generalization in Remote Sensing

2023-11-27 · Avigyan Bhattacharya, Mainak Singha, Ankit Jha, Biplab Banerjee

We focus on domain and class generalization problems in analyzing optical remote sensing images, using the large-scale pre-trained vision-language model (VLM), CLIP. While contrastively trained VLMs show impressive zero-…

Language ModellingPrompt LearningZero-shot Generalization

Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification

2024-09-01 · Karim El Khoury, Maxime Zanella, Benoît Gérin, Tiffanie Godelaine 외

Vision-Language Models for remote sensing have shown promising uses thanks to their extensive pretraining. However, their conventional usage in zero-shot scene classification methods still involves dividing large images …

Scene ClassificationTransductive Zero-Shot Classificationzero-shot-classificationZero-Shot Learning

LR-FPN: Enhancing Remote Sensing Object Detection with Location Refined Feature Pyramid Network

2024-04-02 · Hanqian Li, Ruinan Zhang, Ye Pan, Junchi Ren 외

Remote sensing target detection aims to identify and locate critical targets within remote sensing images, finding extensive applications in agriculture and urban planning. Feature pyramid networks (FPNs) are commonly us…

Objectobject-detectionObject Detection