LFX: Towards Unified Light Field Dense Semantic Segmentation and Salient Object Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913151398707200 |
|---|---|
| author | Teng, Fei Huang, Lingxin Deng, Buyin Luo, Kai Zheng, Boyuan Fang, Zheng Zheng, Hong Peng, Kunyu Zhang, Jiaming Wang, Yaonan Yang, Kailun |
| author_facet | Teng, Fei Huang, Lingxin Deng, Buyin Luo, Kai Zheng, Boyuan Fang, Zheng Zheng, Hong Peng, Kunyu Zhang, Jiaming Wang, Yaonan Yang, Kailun |
| contents | Light field cameras capture multi-view observations within a single exposure. However, existing studies are typically tailored to specific LF representations, leaving the field without a unified learning framework. To bridge this gap, we present LFX, the first unified framework for LF perception. LFX establishes a representation-invariant feature modulation space, enabling it to adapt to heterogeneous LF representations and diverse perception tasks. Specifically, we propose Field-of-Parallax Angular Subspace Modeling (FoP-ASM), which assigns an independent angular marker to each auxiliary view, enabling view-wise independent modeling. Meanwhile, shared manifold subspace constraints and regularization losses enforce globally consistent semantic modulation across views. Extensive evaluations across three LF benchmarks show that LFX achieves state-of-the-art results across distinct LF representations, outperforming representation-specific methods by up to 12% and 20% with 0.029/0.027 MAE for salient object detection, and achieving 84.37 mIoU for semantic segmentation. The source code will be made publicly available at https://github.com/FeiT-FeiTeng/LFX. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00747 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LFX: Towards Unified Light Field Dense Semantic Segmentation and Salient Object Detection Teng, Fei Huang, Lingxin Deng, Buyin Luo, Kai Zheng, Boyuan Fang, Zheng Zheng, Hong Peng, Kunyu Zhang, Jiaming Wang, Yaonan Yang, Kailun Computer Vision and Pattern Recognition Robotics Image and Video Processing Light field cameras capture multi-view observations within a single exposure. However, existing studies are typically tailored to specific LF representations, leaving the field without a unified learning framework. To bridge this gap, we present LFX, the first unified framework for LF perception. LFX establishes a representation-invariant feature modulation space, enabling it to adapt to heterogeneous LF representations and diverse perception tasks. Specifically, we propose Field-of-Parallax Angular Subspace Modeling (FoP-ASM), which assigns an independent angular marker to each auxiliary view, enabling view-wise independent modeling. Meanwhile, shared manifold subspace constraints and regularization losses enforce globally consistent semantic modulation across views. Extensive evaluations across three LF benchmarks show that LFX achieves state-of-the-art results across distinct LF representations, outperforming representation-specific methods by up to 12% and 20% with 0.029/0.027 MAE for salient object detection, and achieving 84.37 mIoU for semantic segmentation. The source code will be made publicly available at https://github.com/FeiT-FeiTeng/LFX. |
| title | LFX: Towards Unified Light Field Dense Semantic Segmentation and Salient Object Detection |
| topic | Computer Vision and Pattern Recognition Robotics Image and Video Processing |
| url | https://arxiv.org/abs/2503.00747 |