LFSamba: Marry SAM with Mamba for Light Field Salient Object Detection

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Zhengyi, Wang, Longzhen, Fang, Xianyong, Tu, Zhengzheng, Wang, Linbo
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915013006983168
author Liu, Zhengyi
Wang, Longzhen
Fang, Xianyong
Tu, Zhengzheng
Wang, Linbo
author_facet Liu, Zhengyi
Wang, Longzhen
Fang, Xianyong
Tu, Zhengzheng
Wang, Linbo
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2411_06652
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LFSamba: Marry SAM with Mamba for Light Field Salient Object Detection
Liu, Zhengyi
Wang, Longzhen
Fang, Xianyong
Tu, Zhengzheng
Wang, Linbo
Computer Vision and Pattern Recognition
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
title LFSamba: Marry SAM with Mamba for Light Field Salient Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.06652