Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Detail-Preserving Transformer for Light Field Image Super-Resolution

About

Recently, numerous algorithms have been developed to tackle the problem of light field super-resolution (LFSR), i.e., super-resolving low-resolution light fields to gain high-resolution views. Despite delivering encouraging results, these approaches are all convolution-based, and are naturally weak in global relation modeling of sub-aperture images necessarily to characterize the inherent structure of light fields. In this paper, we put forth a novel formulation built upon Transformers, by treating LFSR as a sequence-to-sequence reconstruction task. In particular, our model regards sub-aperture images of each vertical or horizontal angular view as a sequence, and establishes long-range geometric dependencies within each sequence via a spatial-angular locally-enhanced self-attention layer, which maintains the locality of each sub-aperture image as well. Additionally, to better recover image details, we propose a detail-preserving Transformer (termed as DPT), by leveraging gradient maps of light field to guide the sequence learning. DPT consists of two branches, with each associated with a Transformer for learning from an original or gradient image sequence. The two branches are finally fused to obtain comprehensive feature representations for reconstruction. Evaluations are conducted on a number of light field datasets, including real-world scenes and synthetic data. The proposed method achieves superior performance comparing with other state-of-the-art schemes. Our code is publicly available at: https://github.com/BITszwang/DPT.

Shunzhou Wang, Tianfei Zhou, Yao Lu, Huijun Di• 2022

Related benchmarks

TaskDatasetResultRank
Light Field Image Super-ResolutionHCIold 2x scale (test)
PSNR44.3
11
Light Field Image Super-ResolutionINRIA 2x scale (test)
PSNR36.41
11
Light Field Image Super-ResolutionAverage 2x scale (test)
PSNR38.4
11
Light Field Image Super-ResolutionEPFL 2x scale (test)
PSNR34.49
11
Light Field Image Super-ResolutionSTFgantry 2x scale (test)
PSNR39.43
11
Light Field Image Super-ResolutionEPFL 4x scale (test)
PSNR28.94
11
Light Field Image Super-ResolutionHCInew 4x scale (test)
PSNR31.2
11
Light Field Image Super-ResolutionHCIold 4x scale (test)
PSNR37.41
11
Light Field Image Super-ResolutionINRIA 4x scale (test)
PSNR30.96
11
Light Field Image Super-ResolutionSTFgantry 4x scale (test)
PSNR31.15
11
Showing 10 of 12 rows

Other info

Follow for update