FPGA Based Video Transcoding System with 2K-4K Super-Resolution Conversion

Wei, Yuzhuo; Chen, Li; Xie, Rong; Song, Li; Zhang, Xiaoyun; Gao, Zhiyong

doi:10.1109/vcip47243.2019.8966063

Cited by 4 publications

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Single image super-resolution (SISR) is to restore a degraded low-resolution (LR) image to a texture-realistic high-resolution (HR) image [11]. SISR has a wide range of applications in surveillance [39], astronomy [8], medical imaging [7], film and television [23,14], and other industries [26,37,33]. With the development of deep learning, SISR has made great progress over these years [4,5,16,18,13,40,31,19,3,22].…”

Section: Introductionmentioning

confidence: 99%

LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution

Zhang¹,

Li²,

He³

et al. 2023

Preprint

View full text Add to dashboard Cite

It is widely agreed that reference-based super-resolution (RefSR) achieves superior results by referring to similar high quality images, compared to single image superresolution (SISR). Intuitively, the more references, the better performance. However, previous RefSR methods have all focused on single-reference image training, while multiple reference images are often available in testing or practical applications. The root cause of such trainingtesting mismatch is the absence of publicly available multireference SR training datasets, which greatly hinders research efforts on multi-reference super-resolution. To this end, we construct a large-scale, multi-reference superresolution dataset, named LMR. It contains 112,142 groups of 300×300 training images, which is 10× of the existing largest RefSR dataset. The image size is also much larger. More importantly, each group is equipped with 5 reference images with different similarity levels. Furthermore, we propose a new baseline method for multireference super-resolution: MRefSR, including a Multi-Reference Attention Module (MAM) for feature fusion of an arbitrary number of reference images, and a Spatial Aware Filtering Module (SAFM) for the fused feature selection. The proposed MRefSR achieves significant improvements over state-of-the-art approaches on both quantitative and qualitative evaluations. https://github. com/wdmwhh/MRefSR

show abstract