An Efficient Quality Metric for Video Frame Interpolation

Metadata

Publisher: SMPTE
Doc Type: Journal Article
Content Type: Original Research
Abbreviated Title: SMPTE Motion Imaging Jour.
Volume: 135, No. 4, pp. 25–33
Abstract: Video Frame Interpolation (VFI) enhances temporal video quality for applications like slow-motion effects and broadcast frame-rate conversion. While modern VFI methods that use optical flow and deep networks can handle complex motion and occlusions, evaluating the quality of interpolated content remains challenging. Traditional metrics like peak signal-to-noise ratio (PSNR) and Stuctural Similarity Index (SSIM) ignore temporal information, while perceptual metrics like Learned Perceptual Image Patch Similarity (LPIPS) focus only on spatial aspects. Recent VFI-specific metrics, such as FloLPIPS, incorporate motion-field errors to detect temporal inconsistencies but are computationally expensive, limiting their practical use in training or real-time assessment. Building on previous work in motion picture restoration, we developed PSNR DIV , which uses divergence to detect irregularities in motion fields. As such, we can identify problematic motion field patterns that degrade the quality of interpolated frames. PSNR DIV requires only one sequence's motion field, thereby reducing computational load. Evaluation on the Bristol Video Intelligence (BVI)-VFI dataset shows statistically significant improvements over FloLPIPS. It achieves these gains while being 2.5x faster and using 6x less memory.
Publication Date: 2026-07-01
DOI: 10.5594/JMI.2026/WZPJ1373
ISSN: Print: 1545-0279 | Electronic: 2160-2492
Link: https://doi.org/10.5594/JMI.2026/WZPJ1373
Author(s): Conall Daly
Darren Ramsook
Anil C. Kokaram
Keyword(s): Video Frame Interpolation Quality, Temporal Consistency Metrics
Copyright: © 2026 SMPTE

Bibliographic Reference(s)

A. Paliwal and N. Khademi Kalantari, “Deep Slow Motion Video Reconstruction With Hybrid Imaging System,” IEEE Trans. Pattern Anal. Mach. Intell., 42 (7): 1557–1569, 2020. EXTERNAL
K. M. Briedis, A. Djelouah, M. Meyer, I. McGonigal, M. Gross, and C. Schroers, “Neural Frame Interpolation for Rendered Content,” ACM Trans. Graph., 40 (6): 1–13, 2021. EXTERNAL
Y. Guo, L. Chen, Z. Gao, and X. Zhang, “Frame Rate Up-Conversion Method for Video Processing Applications,” IEEE Trans. Broadcast., 60 (4): 659–669, 2014. EXTERNAL
Z. Teed and J. Deng, “RAFT: Recurrent All-Pairs Field Transforms for Optical Flow,” Proc. Eur. Cont. Comput. Vis. (ECCV), 2020. EXTERNAL
Z. Liu, R. A. Yeh, X. Tang, Y. Liu, and A. Agarwala, “Video Frame Synthesis Using Deep Voxel Flow,” Proc. IEEE Int. Cont. Comput. Vis. (ICCV), 2017. EXTERNAL
S. Niklaus, L. Mai, and F. Liu, “Video Frame Interpolation via Adaptive Separable Convolution,” Proc. IEEE Int. Cont. Comput. Vis. (ICCV), 2017. EXTERNAL
D. Danier, F. Zhang, and D. Bull, “ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation,” Proc. IEEE/CVF Cont. Comput. Vis. Pattern Recognit. (CVPR), 2022. EXTERNAL
Z. Shi, X. Xu, X. Liu, J. Chen, and M. H. Yang, “Video Frame Interpolation Transformer,” Proc. IEEE/CVF Cont. Comput. Vis. Pattern Recognit. (CVPR), 2022. EXTERNAL
R. Zhang, P. Isola, A. A. Efros, E. Shechtman, and O. Wang, “The Unreasonable Effectiveness of Deep Features as a Perceptual Metric,” Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018. EXTERNAL
A. Mackin, K. C. Noland, and D. R. Bull, “High Frame Rates and the Visibility of Motion Artifacts,” SMPTE Motion Imaging J., 126 (5): 41–51, 2017. EXTERNAL
D. Danier, F. Zhang, and D. Bull, “A Subjective Quality Study for Video Frame Interpolation,” Proc. IEEE Int. Conf. Image Process. (ICIP), 2022. EXTERNAL
S. Ge, A. Mahapatra, G. Parmar, J. Y. Zhu, and J. B. Huang, “On the Content Bias in Fréchet Video Distance,” Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2024. EXTERNAL
D. Danier, F. Zhang, and D. Bull, “FloLPIPS: A Bespoke Video Quality Metric for Frame Interpolation,” Proc. IEEE Picture Coding Symp. (PCS), 2022. EXTERNAL
C. Daly, D. Ramsook, and A. Kokaram, “An Efficient Quality Metric for Video Frame Interpolation Based on Motion-Field Divergence,” Proc. IEEE Int. Conf. Quality Multimedia Experience (QoMEX), 2025. EXTERNAL
Video Quality Experts Group, Final Report From the Video Quality Experts Group on the Validation of Objective Quality Metrics for Video Quality Assessment, 2000. EXTERNAL
J. Han, X. Min, J. Jia, Y. Gao, X. Liu, and G. Zhai, “Full-Reference and No-Reference Quality Assessment for Video Frame Interpolation,” IEEE Trans. Circuits Syst. Video Technol., 36 (7): 6575–6588, 2025. EXTERNAL
Q. Hou, A. Ghildyal, and F. Liu, “A Perceptual Quality Metric for Video Frame Interpolation,” Proc. Eur. Cont. Comput. Vis. (ECCV), 2022. EXTERNAL
G. M. Çökmez, Y. Zhang, C. Schroers, and T. O. Aydin, “CLIP-Fusion: A Spatio-Temporal Quality Metric for Frame Interpolation,” Proc. IEEE/CVF Winter Conf. Appl. Comput. Vis. (WACV), 2025. EXTERNAL
D. Danier, F. Zhang, and D. Bull, “BVI-VFI: A Video Quality Database for Video Frame Interpolation,” IEEE Trans. Image Process., 32: 6004–6019, 2023. EXTERNAL
D. Corrigan, N. Harte, and A. Kokaram, “Pathological Motion Detection for Robust Missing Data Treatment in Degraded Archived Media,” Proc. IEEE Int. Conf. Image Process. (ICIP), 2006. EXTERNAL
X. Xu, L. Siyao, W. Sun, Q. Yin, and M. Yang, “Quadratic Video Interpolation,” Proc. Int. Conf. Neural Int. Process. Syst. (NeurIPS), 2019. EXTERNAL
International Telecommunication Union-Telecommunication (ITU-T), “Recommendation ITU-T P.910: Subjective Video Quality Assessment Methods for Multimedia Applications,” 2000. EXTERNAL
G. Farnebäck, “Two-Frame Motion Estimation Based on Polynomial Expansion,” Proc. Scand. Conf. Image Anal. (SCIA), 2003. EXTERNAL

Source Data (JSON)

Full registry record with provenance metadata. Open directly: /api/doc/10.5594-JMI.2026-WZPJ1373.json

Reference Tree

Explore all references and references to this document, as a navigable tree.

Open Reference Tree

Reference this Doc

Plain text (ISO 690 compliant)

Preview:

Conall Daly, Darren Ramsook, and Anil C. Kokaram; An Efficient Quality Metric for Video Frame Interpolation, MIJ 2026, Volume 135, Number 4 (pp. 25 to 33); SMPTE, 2026. Available at https://doi.org/10.5594/JMI.2026/WZPJ1373

Snippet:

Conall Daly, Darren Ramsook, and Anil C. Kokaram; An Efficient Quality Metric for Video Frame Interpolation, MIJ 2026, Volume 135, Number 4 (pp. 25 to 33); SMPTE, 2026. Available at https://doi.org/10.5594/JMI.2026/WZPJ1373

HTML (ISO 690 compliant)

Preview:

Snippet:

<span class="citation">Conall Daly, Darren Ramsook, and Anil C. Kokaram; <cite>An Efficient Quality Metric for Video Frame Interpolation</cite>, MIJ 2026, Volume 135, Number 4 (pp. 25 to 33); SMPTE, 2026. Available at <a href="https://doi.org/10.5594/JMI.2026/WZPJ1373" target="_blank" rel="noopener">https://doi.org/10.5594/JMI.2026/WZPJ1373</a></span>

SMPTE's HTML Pub

Preview:

Conall Daly, Darren Ramsook, and Anil C. Kokaram; An Efficient Quality Metric for Video Frame Interpolation, MIJ 2026, Volume 135, Number 4 (pp. 25 to 33); SMPTE, 2026
doi: 10.5594/JMI.2026/WZPJ1373
url: https://doi.org/10.5594/JMI.2026/WZPJ1373

Snippet:

<li>
Conall Daly, Darren Ramsook, and Anil C. Kokaram; <cite id="bib-10-5594-jmi-2026-wzpj1373">An Efficient Quality Metric for Video Frame Interpolation</cite>, MIJ 2026, Volume 135, Number 4 (pp. 25 to 33); SMPTE, 2026
<span class="doi">10.5594/JMI.2026/WZPJ1373</span>
</li>