MRF-SA: Multi-Receptive Field Spatial–Angular Framework for Light Field Angular Super-Resolution

Abstract

Light field angular super-resolution (LFASR) aims to reconstruct densely sampled views from sparse inputs by exploiting spatial–angular correlations, thereby producing rich spatial–angular representations and enabling applications such as 3D reconstruction, refocusing, and virtual reality. In this paper, we propose a multi-receptive field spatial–angular (MRF-SA) framework that jointly captures fine-grained details and long-range dependencies through complementary spatial and angular branches. This design enables effective modeling of disparity-aware interactions without relying on computationally expensive attention mechanisms. In addition, we introduce a lightweight variant based on depth-wise separable convolutions to achieve a favorable tradeoff between reconstruction accuracy and computational efficiency. Extensive experiments on both real-world and synthetic datasets demonstrate that the proposed method achieves competitive performance compared to state-of-the-art approaches.