Browse State-of-the-Art › Video Frame Interpolation

Video Frame Interpolation

114 papers with code · 21 benchmarks · 15 datasets archive 2025-07-28

Computer Vision

The goal of Video Frame Interpolation is to synthesize several frames in the middle of two adjacent frames of the original video. Video Frame Interpolation can be applied to generate slow motion video, increase video frame rate, and frame recovery in video streaming.

Source: Reducing the X-ray radiation exposure frequency in cardio-angiography via deep-learning based video interpolation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

21 leaderboard tables shown for this task, 21 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 21 until expanded.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
MSU Video Frame Interpolation (24 rows) RIFE RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation code Syntology ran 19 of 26 samples · 7 unverified Compare
Vimeo90K (23 rows) MA-CSPA Exploring Motion Ambiguity and Alignment for High-Quality Video... — — Compare
X4K1000FPS (20 rows) HiFI High-Resolution Frame Interpolation with Patch-based Cascaded Diffusion — — Compare
UCF101 (19 rows) EMA-VFI Extracting Motion and Appearance via Inter-Frame Attention for... code Syntology ran 10 of 12 samples · 2 unverified Compare
Middlebury (11 rows) IFRNet IFRNet: Intermediate Feature Refine Network for Efficient Frame... code Syntology ran 10 of 20 samples · 10 unverified Compare
SNU-FILM (easy) (8 rows) ST-MFNet ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation code — Compare
SNU-FILM (extreme) (8 rows) DBVI Deep Bayesian Video Frame Interpolation code — Compare
SNU-FILM (hard) (8 rows) ST-MFNet ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation code — Compare
SNU-FILM (medium) (8 rows) ST-MFNet ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation code — Compare
Vid4 - 4x upscaling (5 rows) VRT VRT: A Video Restoration Transformer code Syntology ran 4 of 5 samples · 1 unverified Compare
X4K1000FPS-2K (4 rows) VFIMamba VFIMamba: Video Frame Interpolation with State Space Models code Syntology ran 8 of 8 samples · 0 unverified Compare
Xiph-2K (4 rows) VFIMamba VFIMamba: Video Frame Interpolation with State Space Models code Syntology ran 8 of 8 samples · 0 unverified Compare
LAVIB (3 rows) FLAVR LAVIB: A Large-scale Video Interpolation Benchmark code Syntology ran 8 of 9 samples · 1 unverified Compare
Xiph-4k (3 rows) EMA-VFI Extracting Motion and Appearance via Inter-Frame Attention for... code Syntology ran 10 of 12 samples · 2 unverified Compare
DAVIS (2 rows) DBVI Deep Bayesian Video Frame Interpolation code — Compare
GoPro (2 rows) DBVI Deep Bayesian Video Frame Interpolation code — Compare
ATD-12K (1 row) M2M-PWC Many-to-many Splatting for Efficient Video Frame Interpolation code — Compare
Nvidia Dynamic Scene (1 row) CURE Learning Cross-Video Neural Representations for High-Quality Frame... code Syntology ran 3 of 7 samples · 4 unverified Compare
VFITex (1 row) ST-MFNet ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation code — Compare
Xiph 4k (1 row) CURE Learning Cross-Video Neural Representations for High-Quality Frame... code Syntology ran 3 of 7 samples · 4 unverified Compare
Xiph-4K (Crop) (1 row) M2M-PWC Many-to-many Splatting for Efficient Video Frame Interpolation code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

15 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

3 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 114 papers with code (204 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

Syntology lines on 12 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections