MMO-IG: Multi-Class and Multi-Scale Object Image Generation for Remote Sensing

TL;DR

This paper introduces MMO-IG, a novel deep generative model for remote sensing images that synthesizes multi-class, multi-scale objects with labels, improving data augmentation and detection performance.

Contribution

We propose MMO-IG, a multi-class, multi-scale remote sensing image generator using diffusion models, spatial-cross dependency knowledge graph, and structured object distribution instructions.

Findings

Superior generation of dense MMO-supervised RS images.

Enhanced RS object detection performance with pre-trained MMO-IG.

Effective modeling of complex object interdependencies in RS images.

Abstract

The rapid advancement of deep generative models (DGMs) has significantly advanced research in computer vision, providing a cost-effective alternative to acquiring vast quantities of expensive imagery. However, existing methods predominantly focus on synthesizing remote sensing (RS) images aligned with real images in a global layout view, which limits their applicability in RS image object detection (RSIOD) research. To address these challenges, we propose a multi-class and multi-scale object image generator based on DGMs, termed MMO-IG, designed to generate RS images with supervised object labels from global and local aspects simultaneously. Specifically, from the local view, MMO-IG encodes various RS instances using an iso-spacing instance map (ISIM). During the generation process, it decodes each instance region with iso-spacing value in ISIM-corresponding to both background and foreground instances-to produce RS images through the denoising process of diffusion models. Considering the complex interdependencies among MMOs, we construct a spatial-cross dependency knowledge graph (SCDKG). This ensures a realistic and reliable multidirectional distribution among MMOs for region embedding, thereby reducing the discrepancy between source and target domains. Besides, we propose a structured object distribution instruction (SODI) to guide the generation of synthesized RS image content from a global aspect with SCDKG-based ISIM together. Extensive experimental results demonstrate that our MMO-IG exhibits superior generation capabilities for RS images with dense MMO-supervised labels, and RS detectors pre-trained with MMO-IG show excellent performance on real-world datasets.