Video Frame Interpolation Rankings
and Video Deblurring Rankings

Gradually I intend to add new rankings, but my priority is to keep the existing ones up to date. Below is a list of 3 upcoming updates that I intend to add to keep the existing rankings up to date:

1. Add enhanced models: [arXiv]
2. Add enhanced models: [arXiv]
3. Add missing model: VFIFT [arXiv]

I will also gradually change the layout of tables, so the old and new layouts of the tables will appear simultaneously for some time. In the near future I will write a little more information about what inspired me to add my new repository: Monocular Depth Estimation Rankings and 2D to 3D Video Conversion Rankings

---

Researchers! Please train at least one of your models on perceptual loss. I have made a special column in my rankings dedicated specifically to such models. Why models trained on perceptual loss? This is best summarised by the following quote ¹:

"the model trained using color loss 𝓛_Lap performs best in terms of PSNR and SSIM whereas the one trained using perceptual loss 𝓛_F performs best in terms of LPIPS. We further note that the 𝓛_F-trained model better recovers fine details in challenging cases, making it preferable in practice."

It can be seen from the results of two video frame interpolation models from the quote above on the Vimeo-90K triplet test set ¹:

Model	PSNR ↑	SSIM ↑	LPIPS ↓
SoftSplat - 𝓛Lap	36.10dB	0.970	0.021
SoftSplat - 𝓛F	35.48dB	0.964	0.013

Sometimes even almost 3dB better PSNR result does not guarantee better LPIPS result, as shown by the results of two different video frame interpolation methods on the Vimeo-90K septuplet test set ²:

Model	PSNR ↑	SSIM ↑	LPIPS ↓
VFIT-B	36.963dB	0.9649	0.0304
RIFE	34.048dB	0.9449	0.0233

LPIPS ³ is a metric that reflects human perception much better than PSNR or SSIM, which is also evident from the results presented in the paper of the competitive perceptual metric ⁴:

IQA Model	BAPPS database Frame interpolation 2AFC score ↑	BAPPS database Video deblurring 2AFC score ↑	Ding20 database Deblurring 2AFC score ↑
Human	0.686	0.671	0.843
LPIPS	0.630	0.605	0.788
PSNR	0.543	0.590	0.518
SSIM	0.548	0.583	0.575

List of Rankings

Each ranking includes only the best model for one method.

The rankings exclude all event-based models.

Joint Video Deblurring and Frame Interpolation Rankings

1. 👑 RBI with real motion blur✔️: LPIPS😍 (no data)
   This will be the King of all rankings. We look forward to ambitious researchers.
2. RBI with real motion blur✔️: PSNR😞>=28.5dB
3. Adobe240 (640×352) with synthetic motion blur✖️: LPIPS😍 (no data)
4. Adobe240 (640×352) with synthetic motion blur✖️: PSNR😞>=33.3dB
5. Adobe240 (5:8) with synthetic motion blur✖️: LPIPS😍 (no data)
6. Adobe240 (5:8) with synthetic motion blur✖️: PSNR😞>=25dB

Video Deblurring Rankings

• (to do)

Video Frame Interpolation Rankings

1. Vimeo-90K triplet: LPIPS😍(SqueezeNet)<=0.014
2. Vimeo-90K triplet: LPIPS😍<=0.018
3. Vimeo-90K triplet: PSNR😞>=36dB
4. Vimeo-90K septuplet: LPIPS😍<=0.032
5. Vimeo-90K septuplet: PSNR😞>=36dB

Appendices

• Appendix 1: Rules for qualifying models for the rankings (to do)
• Appendix 2: Metrics selection for the rankings

---

RBI with real motion blur✔️: PSNR😞>=28.5dB

RK	Model	PSNR ↑    {Input fr.}	Training dataset	Official   repository	Practical model	VapourSynth
1	Pre-BiT++	31.32 {3}	Pretraining: Adobe240 Training: RBI			-
2	DeMFI-Netrb(5,3)	29.03 {4}	RBI		-	-
3	PRF4 -Large ENH:	28.55 {5}	RBI		-	-

Adobe240 (640×352) with synthetic motion blur✖️: PSNR😞>=33.3dB

RK	Model	PSNR ↑    {Input fr.}	Originally announced or Training dataset	Official   repository	Practical model	VapourSynth
1	BVFI	35.43 {4}	Adobe240	-	-	-
2	BiT++	34.97 {3}	Adobe240			-
3	DeMFI-Netrb(5,3)	34.34 {4}	Adobe240		-	-
4	ALANET	33.34dB 5	August 2020 5		-	-
5	PRF4 -Large	33.32dB 6	February 2020 7		-	-

Adobe240 (5:8) with synthetic motion blur✖️: PSNR😞>=25dB

RK	Model	PSNR ↑	Originally announced	Official   repository	Practical model	VapourSynth
1	VIDUE	28.74dB 8	March 2023 8		-	-
2	FLAVR	27.23dB 8	December 2020 9		-	-
3	UTI-VFI	26.69dB 8	December 2020 10		-	-
4	DeMFI	25.71dB 8	November 2021 11		-	-

Vimeo-90K triplet: LPIPS😍(SqueezeNet)<=0.014

RK	Model	LPIPS ↓	Originally announced	Official   repository	Practical model	VapourSynth
1	CDFI w/ adaP/U	0.008 12	March 2021 13		-	-
2	EDSC_s-𝓛F	0.010 13	June 2020 14		EDSC_s-𝓛F	-
3	DRVI	0.013 15	August 2021 15	-	-	-

Vimeo-90K triplet: LPIPS😍<=0.018

RK	Model	LPIPS ↓    {Input fr.}	Training dataset	Official   repository	Practical model	VapourSynth
1	EAFI-𝓛ecp	0.012 {2}	Vimeo-90K triplet	-	EAFI-𝓛ecp	-
2	UGFI 𝓛S	0.0126 {2}	Vimeo-90K triplet	-	UGFI 𝓛S	-
3	SoftSplat - 𝓛F	0.013 {2}	Vimeo-90K triplet		SoftSplat - 𝓛F	-
4	FILM-𝓛S	0.0132 {2}	Vimeo-90K triplet		FILM-𝓛S	-
5	EDSC_s-𝓛F	0.016 {2}	Vimeo-90K triplet		EDSC_s-𝓛F	-
6	CtxSyn - 𝓛F	0.017 {2}	proprietary	-	CtxSyn - 𝓛F	-
7	PerVFI	0.018 {2}	Vimeo-90K triplet	-	PerVFI	-

Vimeo-90K triplet: PSNR😞>=36dB

RK	Model	PSNR ↑    {Input fr.}	Originally announced or Training dataset	Official   repository	Practical model	VapourSynth
1	MA-GCSPA triplet-trained	36.76dB 16	March 2022 16		-	-
2	VFIformer + HRFFM ENH:	36.69 {2}	Vimeo-90K triplet	ENH: -	-	-
3	LADDER-L	36.65 {2}	Vimeo-90K triplet	-	-	-
4	EMA-VFI	36.64dB 17	March 2023 17		-	-
5	DQBC-Aug	36.57dB 18	April 2023 18		-	-
6	TTVFI	36.54dB 19	July 2022 19		-	-
7	AMT-G	36.53dB 20	April 2023 20		-	-
8	AdaFNIO	36.50dB 21	November 2022 21		-	-
9	FGDCN-L	36.46dB 22	November 2022 22		-	-
10	UPR-Net LARGE	36.42dB 23	November 2022 23		-	-
11	EAFI-𝓛ecc	36.38dB 24	July 2022 24	-	EAFI-𝓛ecp	-
12	H-VFI-Large	36.37dB 25	November 2022 25	-	-	-
13	UGFI 𝓛1	36.34 {2}	Vimeo-90K triplet	-	UGFI 𝓛S	-
14	SoftSplat - 𝓛Lap with ensemble	36.28dB 26	March 2020 1		SoftSplat - 𝓛F	-
15	NCM-Large	36.22dB 27	July 2022 27	-	-	-
16-17	IFRNet large	36.20dB 28	May 2022 28		-	-
16-17	RAFT-M2M++ ENH:	36.20 {2}	Vimeo-90K triplet		-	-
18-19	EBME-H*	36.19dB 29	June 2022 29		-	-
18-19	RIFE-Large	36.19 {2}	Vimeo-90K triplet		RIFE v4.15
20-21	ABME	36.18dB 30	August 2021 30		-	-
20-21	ProBoost-Net	36.18 {2}	?	-	-	-
22	TDPNetnv w/o MRTM	36.069 {2}	Vimeo-90K triplet	-	TDPNet	-
23	FILM-𝓛1	36.06 {2}	Vimeo-90K triplet		FILM-𝓛S	-

Vimeo-90K septuplet: LPIPS😍<=0.032

RK	Model	LPIPS ↓	Originally announced	Official   repository	Practical model	VapourSynth
1	RIFE	0.0233 2	November 2020 31		RIFE v4.15
2	IFRNet	0.0274 2	May 2022 28		-	-
3	VFIT-B	0.0304 2	November 2021 32		-	-
4	ABME	0.0309 2	August 2021 30		-	-

Vimeo-90K septuplet: PSNR😞>=36dB

RK	Model	PSNR ↑    {Input fr.}	Originally announced or Training dataset	Official   repository	Practical model	VapourSynth
1	JNMR	37.19dB 33	June 2022 33		-	-
2	VFIT-B	36.96dB 32	November 2021 32		-	-
3	VRT	36.53dB 34	June 2022 (VFI) 34		-	-
4	ST-MFNet	36.507dB 35	November 2021 36		-	-
5	MA-GCSPA septuplet-trained	36.50dB 16	March 2022 16		-	-
6	EDENVFI PVT(15,15)	36.387dB 35	July 2023 35	-	-	-
7	IFRNet	36.37 {2}	Vimeo-90K septuplet		-	-
8	RN-VFI	36.33 {4}	Vimeo-90K septuplet	-	-	-
9	FLAVR	36.25dB 9	December 2020 9		-	-
10	DBVI	36.17dB 37	October 2022 37		-	-
11	EDC	36.14dB 33	February 2022 38		-	-

Appendix 2: Metrics selection for the rankings

Currently, the most commonly used metrics in the existing works on video frame interpolation and video deblurring are: PSNR, SSIM and LPIPS. Exactly in that order.

The main purpose of creating my rankings is to look for the best perceptually-oriented model for practical applications - hence the primary metric in my rankings will be the most common perceptual image quality metric in scientific papers: LPIPS.

At the time of writing these words, in October 2023, in relation to VFI, I have only found another perceptual image quality metric - DISTS in one paper: and also in one paper I found a bespoke VFI metric - FloLPIPS [arXiv]. Unfortunately, both of these papers omit to evaluate the best performing models based on the LPIPS metric. If, in the future, some researcher will evaluate LPIPS top-performing models using alternative, better perceptual metrics, I would of course be happy to add rankings based on those metrics.

I would like to use only one metric - LPIPS. Unfortunately still many of the best VFI and video deblurring methods are only evaluated using PSNR or PSNR and SSIM. For this reason, I will additionally present rankings based on PSNR, which will show the models that can, after perceptually-oriented training, be the best for practical applications, as well as providing a source of knowledge for building even better practical models in the future.

I have decided to completely abandon rankings based on the SSIM metric. Below are the main reasons for this decision, ranked from the most important to the less important.

• The main reason is the following quote, which I found in a paper by researchers at Adobe Research: ²⁶. In the quote they refer to a paper by researchers at NVIDIA: [arXiv].

  We limit the evaluation herein to the PSNR metric since SSIM [57] is subject to unexpected and unintuitive results [39].

• The second reason is, more and more papers are appearing where PSNR scores are given, but without SSIM: ³⁵ and A model from such a paper appearing only in the PSNR-based ranking and at the same time not appearing in the SSIM-based ranking may give the misleading impression that the SSIM score is so poor that it does not exceed the ranking eligibility threshold, while there is simply no SSIM score in a paper.

• The third reason is, that often the SSIM scores of individual models are very close to each other or identical. This is the case in the SNU-FILM Easy test, as shown in Table 3: [CVPR 2023], where as many as 6 models achieve the same score of 0.991 and as many as 5 models achieve the same score of 0.990. In the same test, PSNR makes it easier to determine the order of the ranking, with the same number of significant digits.

• The fourth reason is that PSNR-based rankings are only ancillary when a model does not have an LPIPS score. For this reason, SSIM rankings do not add value to my repository and only reduce its readability.

• The fifth reason is that I want to encourage researchers who want to use only two metrics in their paper to use LPIPS and PSNR instead of PSNR and SSIM.

• The sixth reason is that the time saved by dropping the SSIM-based rankings will allow me to add new rankings based on other test data, which will be more useful and valuable.

Footnotes

1. Softmax Splatting for Video Frame Interpolation [CVPR 2020] [arXiv] ↩ ↩² ↩³

2. Exploring Discontinuity for Video Frame Interpolation [CVPR 2023] [arXiv] ↩ ↩² ↩³ ↩⁴ ↩⁵

3. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric [CVPR 2018] [arXiv] ↩

4. Locally Adaptive Structure and Texture Similarity for Image Quality Assessment [MM 2021] [arXiv] ↩

5. ALANET: Adaptive Latent Attention Network for Joint Video Deblurring and Interpolation [MM 2020] [arXiv] ↩ ↩²

6. Video Frame Interpolation and Enhancement via Pyramid Recurrent Framework [TIP 2020] ↩

7. Blurry Video Frame Interpolation [CVPR 2020] [arXiv] ↩

8. Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time [CVPR 2023] [arXiv] ↩ ↩² ↩³ ↩⁴ ↩⁵

9. FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation [WACV 2023] [arXiv] ↩ ↩² ↩³

10. Video Frame Interpolation without Temporal Priors [NeurIPS 2020] [arXiv] ↩

11. DeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting [ECCV 2022] [arXiv] ↩

12. AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling [TIP 2022] [arXiv] ↩

13. CDFI: Compression-Driven Network Design for Frame Interpolation [CVPR 2021] [arXiv] ↩ ↩²

14. Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution [TPAMI 2021] [arXiv] ↩

15. DRVI: Dual Refinement for Video Interpolation [Access 2021] ↩ ↩²

16. Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation [CVPR 2023] [arXiv] ↩ ↩² ↩³ ↩⁴

17. Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation [CVPR 2023] [arXiv] ↩ ↩²

18. Video Frame Interpolation with Densely Queried Bilateral Correlation [IJCAI 2023] [arXiv] ↩ ↩²

19. TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation [TIP 2023] [arXiv] ↩ ↩²

20. AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation [CVPR 2023] [arXiv] ↩ ↩²

21. AdaFNIO: Adaptive Fourier Neural Interpolation Operator for video frame interpolation [arXiv] ↩ ↩²

22. Flow Guidance Deformable Compensation Network for Video Frame Interpolation [TMM 2023] [arXiv] ↩ ↩²

23. A Unified Pyramid Recurrent Network for Video Frame Interpolation [CVPR 2023] [arXiv] ↩ ↩²

24. Error-Aware Spatial Ensembles for Video Frame Interpolation [arXiv] ↩ ↩²

25. H-VFI: Hierarchical Frame Interpolation for Videos with Large Motions [arXiv] ↩ ↩²

26. Revisiting Adaptive Convolutions for Video Frame Interpolation [WACV 2021] [arXiv] ↩ ↩²

27. Neighbor Correspondence Matching for Flow-based Video Frame Synthesis [MM 2022] [arXiv] ↩ ↩²

28. IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation [CVPR 2022] [arXiv] ↩ ↩² ↩³

29. Enhanced Bi-directional Motion Estimation for Video Frame Interpolation [WACV 2023] [arXiv] ↩ ↩²

30. Asymmetric Bilateral Motion Estimation for Video Frame Interpolation [ICCV 2021] [arXiv] ↩ ↩² ↩³

31. Real-Time Intermediate Flow Estimation for Video Frame Interpolation [ECCV 2022] [arXiv] ↩

32. Video Frame Interpolation Transformer [CVPR 2022] [arXiv] ↩ ↩² ↩³

33. JNMR: Joint Non-linear Motion Regression for Video Frame Interpolation [TIP 2023] [arXiv] ↩ ↩² ↩³

34. VRT: A Video Restoration Transformer [arXiv] ↩ ↩²

35. Efficient Convolution and Transformer-Based Network for Video Frame Interpolation [ICIP 2023] [arXiv] ↩ ↩² ↩³ ↩⁴

36. ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation [CVPR 2022] [arXiv] ↩

37. Deep Bayesian Video Frame Interpolation [ECCV 2022] ↩ ↩²

38. Enhancing Deformable Convolution based Video Frame Interpolation with Coarse-to-fine 3D CNN [ICIP 2022] [arXiv] ↩