FC-VFI: Faithful and Consistent Video Frame Interpolation for High-FPS Slow Motion Video Generation

Ganggui Ding; Hao Chen; Xiaogang Xu

cs.CVMar 5, 2026

FC-VFI: Faithful and Consistent Video Frame Interpolation for High-FPS Slow Motion Video Generation

Authors: Ganggui Ding, Hao Chen, Xiaogang Xu

Organizations: ⋆Zhejiang University · † Chinese University of Hong Kong

Abstract

Large pre-trained video diffusion models excel in video frame interpolation but struggle to generate high fidelity frames due to reliance on intrinsic generative priors, limiting detail preservation from start and end frames. Existing methods often depend on motion control for temporal consistency, yet dense optical flow is error-prone, and sparse points lack structural context. In this paper, we propose FC-VFI for faithful and consistent video frame interpolation, supporting $4\times$ x and $8\times$ interpolation, boosting frame rates from 30 FPS to 120 and 240 FPS at $2560\times 1440$ resolution while preserving visual fidelity and motion consistency. We introduce a temporal modeling strategy on the latent sequences to inherit fidelity cues from start and end frames and leverage semantic matching lines for structure-aware motion guidance, improving motion consistency. Furthermore, we propose a temporal difference loss to mitigate temporal inconsistencies. Extensive experiments show FC-VFI achieves high performance and structural integrity across diverse scenarios.

Figures & tables

Figure 1: Overview of FC-VFI’s training pipeline. (a) We model temporal references by concatenating the noisy latent $\mathbf{z}_{t}^{n}$ with the start and end image latents $\mathbf{z}_{s}$ and $\mathbf{z}_{e}$ along the temporal dimension, enabling the denoising process to reference both boundaries. (b) We apply fidelity modulation by performing a timestep-dependent modulation $t^{*}$ into $\mathbf{z}_{s}$ and $\mathbf{z}_{e}$ , which enhances reference stability. (c) Semantic matching lines featrues $\mathbf{c}_{s}$ and $\mathbf{c}_{e}$ are extracted and encoded from the start frame $\mathbf{I}_{s}$ and end frame $\mathbf{I}_{e}$ , and are element-wise added to $\mathbf{z}_{s}$ and $\mathbf{z}_{e}$ , resulting in enhanced latents $\mathbf{z}_{s}^{\prime}$ and $\mathbf{z}_{e}^{\prime}$ . These are then processed via a copied DiT block to produce $\mathbf{z}_{\text{res}}^{n}$ , which is injected back into the main backbone. (d) The prediction $\hat{\mathbf{v}}_{t}^{n}$ is supervised with a temporal difference loss $\mathcal{L}_{\text{temp}}$ .

Figure 2: Qualitative comparison of interpolation results. (Top) Comparison with GIMM-VFI [ 6 ] on DAVIS-2017 [ 19 ] at $2560\times 1440$ resolution under $8\times$ interpolation. Ours better handles challenging conditions such as high-contrast lighting, small objects, and occlusion, avoiding artifacts like ghosting and structural distortion. (Bottom) Comparison with diffusion-based methods (GI [ 26 ] , ViBiDSampler [ 31 ] , FCVG [ 37 ] ) on X-Test [ 22 ] and DAVIS-2017 at $1024\times 576$ resolution under $8\times$ interpolation. FC-VFI preserves finer details (e.g., text, license plates, building textures), while other methods suffer from motion ambiguity and temporal artifacts.

Methods	$4\times$					$8\times$
Optical-flow-based methods	PSNR $\uparrow$	SSIM $\uparrow$	FID $\downarrow$	FVD $\downarrow$	LPIPS $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	FID $\downarrow$	FVD $\downarrow$	LPIPS $\downarrow$
GIMM-VFI [ 6 ]	29.05	0.901	16.22	125.42	0.061	29.49	0.907	14.75	192.36	0.048
Ours ( $2560\times 1440$ )	30.25	0.915	15.73	130.65	0.054	30.16	0.912	15.50	194.19	0.046
Diffusion-based methods	PSNR $\uparrow$	SSIM $\uparrow$	FID $\downarrow$	FVD $\downarrow$	LPIPS $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	FID $\downarrow$	FVD $\downarrow$	LPIPS $\downarrow$
GI [ 26 ]	20.96	0.847	37.58	1310.80	0.119	21.05	0.694	39.24	940.72	0.128
ViBiDSampler [ 31 ]	23.48	0.764	31.92	1375.15	0.107	20.99	0.699	36.74	978.68	0.125

Table 1: Quantitative comparison with optical-flow-based methods (evaluated at

2560\times 1440

) and diffusion-based methods (evaluated at

1024\times 576

) under

4\times

and

8\times

interpolation settings.

Methods	$4\times$					$8\times$
Different Variants	PSNR $\uparrow$	SSIM $\uparrow$	FID $\downarrow$	FVD $\downarrow$	LPIPS $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	FID $\downarrow$	FVD $\downarrow$	LPIPS $\downarrow$
Channel Reference	26.07	0.868	68.16	293.83	0.1067	24.73	0.839	70.19	501.84	0.1359
Temporal Reference (our baseline)	29.83	0.921	24.79	185.67	0.0672	27.34	0.893	32.33	407.10	0.1021
+ Fidelity Modulation (Sec. 2.2 )	30.65	0.925	14.78	178.82	0.0552	28.69	0.906	20.42	326.37	0.0832
+ $\mathcal{L}_{\text{temp}}$ (Sec. 2.3 )	30.75	0.926	15.48	165.87	0.0548	28.67	0.907	19.96	312.64	0.0845
+ Matching Lines Condition (Sec. 2.4 )	30.89	0.928	17.19	153.34	0.0550	29.13	0.912	21.44	302.04	0.0832

Table 2: Ablation study demonstrating the impact of temporal reference (baseline), fidelity modulation, temporal difference loss

\mathcal{L}_{\text{temp}}

, and matching lines condition on interpolation quality. A channel reference (the variant using only channel-wise concatenation) is also included for comparison. Metrics are reported for

4\times

and

8\times

settings.

Method	NFE	Time (s) ( $4\times$ )	Time (s) ( $8\times$ )	Resolution
GI [ 26 ]	300	606	606	1024 $\times$ 576
ViBiDSampler [ 31 ]	50	23	38	1024 $\times$ 576
FCVG [ 37 ]	50	89	145	1024 $\times$ 576
Ours	10	16	22	1024 $\times$ 576
Ours	10	27	37	1280 $\times$ 720

Table 3: Our method achieves significantly faster inference compared to other diffusion-based approaches.

Figure 3: Ablation results of our method visualized under different module configurations. The displayed intermediate frame is closer to the end frame.

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Panel of Figure 4 — Figure 4: Additional qualitative comparison of interpolation results. (Top) Visual comparisons with GIMM-VFI [ 6 ] at $2560\times 1440$ resolution under $8\times$ interpolation. Tested on additional challenging scenes, our FC-VFI effectively suppresses structural distortion and ghosting artifacts. (Bottom) Visual comparisons with recent diffusion-based methods (GI [ 26 ] , ViBiDSampler [ 31 ] , and FCVG [ 37 ] ) at $1024\times 576$ resolution under $8\times$ interpolation. FC-VFI consistently demonstrates superior capability in recovering fine details (e.g., complex boundaries and textual patterns) and maintaining temporal consistency compared to the baselines (Sec. A.1 ).

Video Frame Interpolation

Video frame interpolation estimates intermediate frames between observed video frames to create smoother playback and reconstruct temporal detail.

See all 26 papers

SNM-VFI: Symmetric Nonlinear Motion-Guided Generative Video Frame Interpolation
Aug 13, 2026Jisoo Jeong, Hong Cai, Jamie Menjay Lin +5Video Diffusion Models Diffusion Guidance
Qualcomm AI Research · Qualcomm Technologies, Inc.
Can Video Diffusion Models Predict Past Frames? Bidirectional Cycle Consistency for Reversible Interpolation
Apr 2, 2026Lingyu Liu, Yaxiong Wang, Li Zhu +1Video Frame Interpolation Video Diffusion Models
School of Software, Xi’an Jiao-tong University, Xi’an, 710049, China. · School of Computer and Information Science, Hefei University of Technology, Jianghuai Advance Technology Center, Anhui Provincial Key Laboratory of Humanoid Robots. Anhui Provincial Industry Innovation Center of Humanoid Robots, Hefei, 230000, China. · Faculty of Science and Technology, and Institute of Collaborative Innovation, University of Macau, Macau, 999078, China.
Following Motion for Sequential Modeling in Video Frame Interpolation
Aug 24, 2026Jaehyun Park, Nam Ik ChoVideo Frame Interpolation Visual SSMs
IPAI, Seoul National University · Department of Electrical and Computer Engineering, INMC, Seoul National University · SNUAILab

Aug 13, 2026J/K move · Enter open · S save

SNM-VFI: Symmetric Nonlinear Motion-Guided Generative Video Frame Interpolation

Jisoo Jeong, Hong Cai, Jamie Menjay Lin, Hanno Ackermann+4

Qualcomm AI Research · Qualcomm Technologies, Inc.

Video Diffusion Models Diffusion Guidance Video Frame Interpolation

Open paper AskPDF arXiv

We propose Symmetric Nonlinear Motion-guided Generative Video Frame Interpolation (SNM-VFI), a training-free framework for motion-controllable generative video frame interpolation with pre-trained optical flow and video diffusion models. Unlike conventional diffusion-based VFI methods that synthesize intermediate frames from random noise, SNM-VFI guides the generative process with correspondence-aware frames produced by a symmetric nonlinear motion model. Specifically, we first utilize a pre-trained optical flow model to construct multi-frame nonlinear flow-based intermediate frames and confidence maps. These flow-guided frames are then encoded as latent priors to initialize and iteratively guide a pre-trained Video Diffusion model, enabling the diffusion model to preserve dense motion correspondence while improving perceptual realism. To further enhance output quality, we employ confidence maps to fuse structurally reliable flow-based predictions with diffusion-generated details in uncertain regions such as occlusions and object boundaries. Extensive evaluations on challenging benchmarks, including DAVIS, Sintel, and KITTI, demonstrate that SNM-VFI achieves strong perceptual quality, competitive reconstruction accuracy, and robust temporal coherence across diverse motion scenarios.

Abstract

Video Frame Interpolation

Explore similar work

SNM-VFI: Symmetric Nonlinear Motion-Guided Generative Video Frame Interpolation

Can Video Diffusion Models Predict Past Frames? Bidirectional Cycle Consistency for Reversible Interpolation

Following Motion for Sequential Modeling in Video Frame Interpolation