Slope-Guided Mamba and Angular-Refined Transformer for Light Field Super-Resolution
2026-07-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the problem of improving the resolution of light field images, which requires carefully connecting details across both space and viewing angles. They point out that previous methods treated spatial and angular information separately, causing inconsistencies, and that some sequence-based methods don't align well with the light field geometry. To solve this, they created a new network called SMART that uses special modules to better link spatial and angular data and to follow the natural geometric structures in the images. Their approach improves image clarity and reduces errors compared to earlier techniques.
Light FieldSuper-ResolutionSpatial-Angular CorrelationEpipolar GeometryTransformersSequence ModelingPSNRImage ArtifactsAngular ModulationManifold Alignment
Authors
Li Jin, Jian Huang, Junde Lu, Shuai Wang, Hao Sheng, Jie Wu
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.