LFX: Towards Unified Light Field Dense Semantic Segmentation and Salient Object Detection
Abstract
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.
Cite
@article{arxiv.2503.00747,
title = {LFX: Towards Unified Light Field Dense Semantic Segmentation and Salient Object Detection},
author = {Fei Teng and Lingxin Huang and Buyin Deng and Kai Luo and Boyuan Zheng and Zheng Fang and Hong Zheng and Kunyu Peng and Jiaming Zhang and Yaonan Wang and Kailun Yang},
journal= {arXiv preprint arXiv:2503.00747},
year = {2026}
}
Comments
The source code will be made publicly available at https://github.com/FeiT-FeiTeng/LFX