LFSamba: Marry SAM with Mamba for Light Field Salient Object Detection
This work addresses a domain-specific problem for applications like virtual reality and robotic vision, but it is incremental as it combines existing methods (SAM and Mamba) for a niche task.
The paper tackles salient object detection in multi-focus light field images by introducing LFSamba, which achieves state-of-the-art performance with a 2.5% improvement in F-measure over previous methods.
A light field camera can reconstruct 3D scenes using captured multi-focus images that contain rich spatial geometric information, enhancing applications in stereoscopic photography, virtual reality, and robotic vision. In this work, a state-of-the-art salient object detection model for multi-focus light field images, called LFSamba, is introduced to emphasize four main insights: (a) Efficient feature extraction, where SAM is used to extract modality-aware discriminative features; (b) Inter-slice relation modeling, leveraging Mamba to capture long-range dependencies across multiple focal slices, thus extracting implicit depth cues; (c) Inter-modal relation modeling, utilizing Mamba to integrate all-focus and multi-focus images, enabling mutual enhancement; (d) Weakly supervised learning capability, developing a scribble annotation dataset from an existing pixel-level mask dataset, establishing the first scribble-supervised baseline for light field salient object detection.https://github.com/liuzywen/LFScribble