DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection

Multi-modal salient object detection (SOD) through the integration of additional data such as depth or thermal information has become a significant task in computer vision during recent years. Traditionally, the challenges of identifying salient objects in RGB, RGB-D (Depth), and RGBT (Thermal) images are tackled separately. However, without intricate cross-modal fusion strategies, such approaches struggle to effectively integrate multi-modal information, often resulting in poorly defined object edges or overconfident inaccurate predictions. Recent studies have shown that designing a unified end-to-end framework to handle all three types of SOD tasks simultaneously is both necessary and difficult. To address this need, we propose a novel approach that treats multi-modal SOD as a conditional mask generation task utilizing diffusion models. We introduce DiMSOD, which enables the concurrent use of local (depth maps, thermal maps) and global controls (original images) within a unified model for progressive denoising and refined prediction. DiMSOD only requires fine-tuning newly introduced modules on a pretrained stable diffusion trained on RGB images, which not only reduces fine-tuning costs for practical applications but also enhances the integration of multi-modal conditional controls. Specifically, we have developed modules including SOD-ControlNet, Feature Adaptive Network (FAN), and Feature Injection Attention Network (FIAN) to enhance the model's performance. Extensive experiments demonstrate that DiMSOD efficiently detects salient objects across RGB, RGB-D, and RGB-T datasets, achieving superior performance compared to previous well-established methods.