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

TL;DR

RASLF is a novel light field super-resolution framework that models structural correlations across multiple representations, improving accuracy and efficiency through innovative modules like PGR, RAAS, and DAA.

Contribution

The paper introduces RASLF, a representation-aware state-space model with new modules for better multi-view correlation modeling and dynamic scanning, enhancing super-resolution performance.

Findings

Achieves state-of-the-art reconstruction accuracy on benchmarks.

Maintains high computational efficiency.

Effectively models multi-view parallax differences.

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.