首个统一光场语义分割与显著目标检测框架，适配多种光场表示。
LFX: Towards Unified Light Field Dense Semantic Segmentation and Salient Object Detection
- 构建不变表示的特征调制空间，支持多类光场输入
- 在3个基准上实现最高性能，显著目标检测MAE低至0.027
- 适合研究光场感知与跨表示学习的开发者
光场相机可在单次曝光中捕捉多视角观测。然而，现有研究通常针对特定光场表示设计，缺乏统一的学习框架。为此，我们提出LFX，首个面向光场感知的统一框架。LFX建立表示无关的特征调制空间，使其可适应异构光场表示及多样感知任务。具体地，我们提出视差角子空间建模（FoP-ASM），为每个辅助视图分配独立的角标记，实现视图级独立建模；同时，共享流形子空间约束与正则化损失确保跨视图全局一致的语义调制。在三个光场基准上的广泛评估表明，LFX在不同光场表示下均达到领先性能，相比特定表示方法提升高达12%和20%，显著目标检测的MAE分别降至0.029/0.027，语义分割达到84.37 mIoU。源代码将公开于https://github.com/FeiT-FeiTeng/LFX。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。