Learning Light Field Angular Super-Resolution via a Geometry-Aware Network
This work addresses the challenge of enhancing angular resolution in light field imaging, particularly for large-baseline scenarios, which is important for applications in computer vision and graphics, though it appears incremental as it builds on existing super-resolution methods with a focus on geometry.
The paper tackles the problem of angular super-resolution for sparsely-sampled light fields with large baselines, which are costly to acquire, by proposing a geometry-aware network that improves PSNR by up to 2 dB on average and reduces execution time by 48× compared to state-of-the-art methods.
The acquisition of light field images with high angular resolution is costly. Although many methods have been proposed to improve the angular resolution of a sparsely-sampled light field, they always focus on the light field with a small baseline, which is captured by a consumer light field camera. By making full use of the intrinsic \textit{geometry} information of light fields, in this paper we propose an end-to-end learning-based approach aiming at angularly super-resolving a sparsely-sampled light field with a large baseline. Our model consists of two learnable modules and a physically-based module. Specifically, it includes a depth estimation module for explicitly modeling the scene geometry, a physically-based warping for novel views synthesis, and a light field blending module specifically designed for light field reconstruction. Moreover, we introduce a novel loss function to promote the preservation of the light field parallax structure. Experimental results over various light field datasets including large baseline light field images demonstrate the significant superiority of our method when compared with state-of-the-art ones, i.e., our method improves the PSNR of the second best method up to 2 dB in average, while saves the execution time 48$\times$. In addition, our method preserves the light field parallax structure better.