English

Slope-Guided Mamba and Angular-Refined Transformer for Light Field Super-Resolution

Computer Vision and Pattern Recognition 2026-07-01 v1

Abstract

Light Field Super-Resolution (LFSR) necessitates accurate modeling of spatial-angular correlations while preserving intrinsic 4D ray coherence. However, maintaining such high-dimensional consistency remains challenging, primarily due to two inherent limitations in prevailing modeling paradigms. First, spatial and angular dimensions are often modeled in a decoupled manner, restricting early cross-dimensional interaction and leading to geometric inconsistencies. Moreover, although continuous sequence modeling paradigms show promise in representing epipolar structures, their rigid scanning mechanisms fundamentally conflict with epipolar geometry, limiting geometry-aware feature aggregation. To address these challenges, we propose a hybrid light field super-resolution network, termed SMART, which integrates a Slope-Guided Mamba and an Angular-Refined Transformer to effectively overcome these limitations. Specifically, we introduce an angular-modulated spatial module to bridge the decoupling gap, incorporating angular priors to strengthen spatial-angular correlation modeling. To mitigate the scan-geometry mismatch, we propose a manifold-aligned trajectory module that enables geometry-consistent sequence modeling along epipolar structures. Experiments on five benchmarks demonstrate that SMART achieves state-of-the-art performance, surpassing previous methods by 0.42 dB (PSNR) with significantly reduced artifacts.

Cite

@article{arxiv.2607.00965,
  title  = {Slope-Guided Mamba and Angular-Refined Transformer for Light Field Super-Resolution},
  author = {Li Jin and Jian Huang and Junde Lu and Shuai Wang and Hao Sheng and Jie Wu},
  journal= {arXiv preprint arXiv:2607.00965},
  year   = {2026}
}

Comments

10 pages, 4 figures, 4 tables. Accepted by IEEE ICME 2026. Hangzhou International Innovation Institute, Beihang University, Hangzhou, China Corresponding author: Jie Wu ([email protected]) Emails: {lijin01, hj, ljd2406107, shuaiwang, shenghao, jiewu}@buaa.edu.cn