BF-STVSR: B-Splines and Fourier-Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Eunjin, Kim, Hyeonjin, Jin, Kyong Hwan, Yoo, Jaejun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910891328405504
author Kim, Eunjin
Kim, Hyeonjin
Jin, Kyong Hwan
Yoo, Jaejun
author_facet Kim, Eunjin
Kim, Hyeonjin
Jin, Kyong Hwan
Yoo, Jaejun
contents While prior methods in Continuous Spatial-Temporal Video Super-Resolution (C-STVSR) employ Implicit Neural Representation (INR) for continuous encoding, they often struggle to capture the complexity of video data, relying on simple coordinate concatenation and pre-trained optical flow networks for motion representation. Interestingly, we find that adding position encoding, contrary to common observations, does not improve--and even degrades--performance. This issue becomes particularly pronounced when combined with pre-trained optical flow networks, which can limit the model's flexibility. To address these issues, we propose BF-STVSR, a C-STVSR framework with two key modules tailored to better represent spatial and temporal characteristics of video: 1) B-spline Mapper for smooth temporal interpolation, and 2) Fourier Mapper for capturing dominant spatial frequencies. Our approach achieves state-of-the-art in various metrics, including PSNR and SSIM, showing enhanced spatial details and natural temporal consistency. Our code is available https://github.com/Eunjnnn/bfstvsr.
format Preprint
id arxiv_https___arxiv_org_abs_2501_11043
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BF-STVSR: B-Splines and Fourier-Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution
Kim, Eunjin
Kim, Hyeonjin
Jin, Kyong Hwan
Yoo, Jaejun
Computer Vision and Pattern Recognition
Artificial Intelligence
While prior methods in Continuous Spatial-Temporal Video Super-Resolution (C-STVSR) employ Implicit Neural Representation (INR) for continuous encoding, they often struggle to capture the complexity of video data, relying on simple coordinate concatenation and pre-trained optical flow networks for motion representation. Interestingly, we find that adding position encoding, contrary to common observations, does not improve--and even degrades--performance. This issue becomes particularly pronounced when combined with pre-trained optical flow networks, which can limit the model's flexibility. To address these issues, we propose BF-STVSR, a C-STVSR framework with two key modules tailored to better represent spatial and temporal characteristics of video: 1) B-spline Mapper for smooth temporal interpolation, and 2) Fourier Mapper for capturing dominant spatial frequencies. Our approach achieves state-of-the-art in various metrics, including PSNR and SSIM, showing enhanced spatial details and natural temporal consistency. Our code is available https://github.com/Eunjnnn/bfstvsr.
title BF-STVSR: B-Splines and Fourier-Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2501.11043