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

MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions for Continuous Space-Time Video Super-Resolution

About

This work addresses continuous space-time video super-resolution (C-STVSR) that aims to up-scale an input video both spatially and temporally by any scaling factors. One key challenge of C-STVSR is to propagate information temporally among the input video frames. To this end, we introduce a space-time local implicit neural function. It has the striking feature of learning forward motion for a continuum of pixels. We motivate the use of forward motion from the perspective of learning individual motion trajectories, as opposed to learning a mixture of motion trajectories with backward motion. To ease motion interpolation, we encode sparsely sampled forward motion extracted from the input video as the contextual input. Along with a reliability-aware splatting and decoding scheme, our framework, termed MoTIF, achieves the state-of-the-art performance on C-STVSR. The source code of MoTIF is available at https://github.com/sichun233746/MoTIF.

Yi-Hsin Chen, Si-Cun Chen, Yi-Hsin Chen, Yen-Yu Lin, Wen-Hsiao Peng• 2023

Related benchmarks

TaskDatasetResultRank
Video Super-ResolutionUDM10 (test)
PSNR24.97
51
Spatiotemporal Video Super-ResolutionBS-ERGB
PSNR24.21
29
Continuous Space-Time Video Super-ResolutionStandard Clip 180x320 resolution
TFLOPs2.043
24
Space-Time Video Super-ResolutionGoPro Average (test)
PSNR30.04
24
Space-Time Video Super-ResolutionAdobe-Average (test)
PSNR29.82
24
Spatiotemporal Video Super-ResolutionGoPro Center
PSNR31.04
15
Spatiotemporal Video Super-ResolutionAdobe240 Center
PSNR30.63
15
Video Super-ResolutionALPIX-VSR
PSNR38.61
4
Showing 8 of 8 rows

Other info

Follow for update