cs.CVMar 2, 2025

LFX: Fusion-Form-Flexible Light Field Modeling for Dense Semantic Segmentation and Salient Object Detection

Authors: Fei Teng, Lingxin Huang, Buyin Deng, Kai Luo, Boyuan Zheng, Zheng Fang, Hong Zheng, Kunyu Peng, 

Organizations: The authors are with the School of Artificial Intelligence and Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, China · The authors are with China Mobile Group Hunan Company Ltd., China. · The author is with the Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Germany.

Abstract

Two distinct light field (LF) observation forms, namely sub-aperture images (S.Aperture images) and focal stack (FS), correspond to two fusion settings: the central image with S.Aperture images (CS) and the central image with FS (CF). Existing LF perception methods are typically form-specific, while a modeling design that can be separately instantiated under either setting remains underexplored. To address this gap, we present LFX, a form-flexible LF perception framework. Here, ``X'' represents the LF observation form, indicating that the one modeling design can be separately instantiated under two fusion settings (CS and CF). Specifically, we propose Field-of-Parallax Angular Subspace Modeling (FoP-ASM), which maps the feature difference between each auxiliary observation and the central image to an observation-specific angular marker. This avoids pairwise modeling among auxiliary observations and form-specific geometric assumptions. Meanwhile, a shared manifold subspace and the associated regularization losses constrain the angular residuals within a common feature space, promoting semantic consistency across auxiliary observations. Extensive evaluations across three LF datasets show that LFX achieves state-of-the-art results across distinct LF forms. Under the S.Aperture images and FS settings, respectively, LFX reduces MAE by 12.12%/20.59% on DUTLF-V2 and by 6.15%/7.69% on HFUT, while achieving the best performance on UrbanLF-real. The source code will be made publicly available at https://github.com/FeiT-FeiTeng/LFX.

Figures & tables

Explore similar work

CardsList
  1. VSANet: View-aware Sparse Attention Network for Light Field Image Denoising

    Jun 23, 2026Gargi Panda, Soumitra Kundu, Saumik Bhattacharya +1light field imagingSparse Attention

  2. RASLF: Representation-Aware State Space Model for Light Field Super-Resolution

    Mar 17, 2026Zeqiang Wei, Kai Jin, Kuan Song +3light field imagingImage Super-Resolution

  3. STAR: Structure-aware Test-time Adaptation for diffusion-based light field Reconstruction

    Sep 17, 2026Wontae Choi, Ki Ryum Moon, Jae Young Lee +2Diffusion Model AdaptationImage Reconstruction