Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Zeqiang Wei, Kai Jin, Kuan Song, Xiuzhuang Zhou, Wenlong Chen, Min Xu

Abstract

Current SSM-based light field super-resolution (LFSR) methods often fail to fully leverage the complementarity among various LF representations, leading to the loss of fine textures and geometric misalignments across views. To address these issues, we propose RASLF, a representation-aware state-space framework that explicitly models structural correlations across multiple LF representations. Specifically, a Progressive Geometric Refinement (PGR) block is created that uses a panoramic epipolar representation to explicitly encode multi-view parallax differences, thereby enabling integration across different LF representations. Furthermore, we introduce a Representation Aware Asymmetric Scanning (RAAS) mechanism that dynamically adjusts scanning paths based on the physical properties of different representation spaces, optimizing the balance between performance and efficiency through path pruning. Additionally, a Dual-Anchor Aggregation (DAA) module improves hierarchical feature flow, reducing redundant deeplayer features and prioritizing important reconstruction information. Experiments on various public benchmarks show that RASLF achieves the highest reconstruction accuracy while remaining highly computationally efficient.

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

Abstract

Current SSM-based light field super-resolution (LFSR) methods often fail to fully leverage the complementarity among various LF representations, leading to the loss of fine textures and geometric misalignments across views. To address these issues, we propose RASLF, a representation-aware state-space framework that explicitly models structural correlations across multiple LF representations. Specifically, a Progressive Geometric Refinement (PGR) block is created that uses a panoramic epipolar representation to explicitly encode multi-view parallax differences, thereby enabling integration across different LF representations. Furthermore, we introduce a Representation Aware Asymmetric Scanning (RAAS) mechanism that dynamically adjusts scanning paths based on the physical properties of different representation spaces, optimizing the balance between performance and efficiency through path pruning. Additionally, a Dual-Anchor Aggregation (DAA) module improves hierarchical feature flow, reducing redundant deeplayer features and prioritizing important reconstruction information. Experiments on various public benchmarks show that RASLF achieves the highest reconstruction accuracy while remaining highly computationally efficient.
Paper Structure (19 sections, 10 equations, 3 figures, 4 tables)

This paper contains 19 sections, 10 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Light Field Representations
  4. Methods based on Spatial-Angular Interaction
  5. Methods based on Geometric Consistency
  6. Methodology
  7. Overview Architecture
  8. Progressive Geometric Refinement
  9. Representation-Aware Asymmetric Scanning Strategy
  10. Dual-Anchor Aggregation Module
  11. Experiments
  12. Datasets and Implementation Details
  13. Comparisons with State-of-The-Art Methods
  14. Ablation Study
  15. Dual-Anchor Aggregation Module
  16. ...and 4 more sections

Figures (3)

  • Figure 1: Overall architecture of the proposed RASLF. (a) The Progressive Geometric Refinement (PGR) paradigm sequentially refines features using representation-specific VSSM units, and a Dual-Anchor Aggregation module fuses multi-stage features via spatial and geometric anchors. (b) Representation-Aware Asymmetric Scanning (RAAS) tailors SS2D scanning paths $\Phi$ and representation transforms $\mathcal{T}, \mathcal{T}^{-1}$ for SAI, MacPI, and EPI, reducing redundant computation while preserving geometry-aware dependencies.
  • Figure 2: Illustration of the Panoramic Epipolar Representation and the corresponding representation-aware scanning paths (indicated by red solid arrows).
  • Figure 3: Qualitative visualization results for 4$\times$ LFSR compared to other methods. Here, we showed the error maps of the reconstructed center-view images, with representative regions indicated by arrows. PSNR/SSIM values for the corresponding region are provided below.