Browse State-of-the-Art › Video Prediction

Video Prediction

208 papers with code · 19 benchmarks · 25 datasets archive 2025-07-28

Computer VisionTime Series

Benchmarks archive 2025-07-28

19 leaderboard tables shown for this task, 19 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 19 until expanded.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
KTH (31 rows) Grid-keypoints Accurate Grid Keypoint Learning for Efficient Video Prediction code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
Moving MNIST (31 rows) PredFormer Video Prediction Transformers without Recurrence or Convolution code — Compare
Kinetics-600 12 frames, 64x64 (16 rows) SiD2 Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion — — Compare
Human3.6M (9 rows) IAM4VP Implicit Stacked Autoregressive Model for Video Prediction code — Compare
BAIR Robot Pushing (6 rows) MAGVIT (-L-FP) MAGVIT: Masked Generative Video Transformer code Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
Cityscapes 128x128 (5 rows) GHVAEs Greedy Hierarchical Variational Autoencoders for Large-Scale Video... — — Compare
SynpickVP (5 rows) MSPred MSPred: Video Prediction at Multiple Spatio-Temporal Scales with... code — Compare
CMU Mocap-2 (4 rows) Latent SDE Scalable Gradients for Stochastic Differential Equations code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified Compare
Cityscapes (3 rows) DMVFN A Dynamic Multi-Scale Voxel Flow Network for Video Prediction code Syntology official (archive's flag): 3 ran · 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
KITTI (3 rows) DMVFN A Dynamic Multi-Scale Voxel Flow Network for Video Prediction code Syntology official (archive's flag): 3 ran · 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
Vimeo90K (3 rows) OPT — — — Compare
CMU Mocap-1 (2 rows) ODE2VAE-KL ODE²VAE: Deep generative second order ODEs with Bayesian neural networks code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified Compare
DAVIS 2017 (2 rows) DMVFN A Dynamic Multi-Scale Voxel Flow Network for Video Prediction code Syntology official (archive's flag): 3 ran · 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
Colored dSprites (1 row) MGP-VAE (with geodesic loss) Disentangling Multiple Features in Video Sequences using Gaussian... code — Compare
KTH 64x64 cond10 pred30 (1 row) SRVP Stochastic Latent Residual Video Prediction code Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
MPI Sintel (1 row) MCnet [villegas2017mcnet] Temporal View Synthesis of Dynamic Scenes through 3D Object Motion... code — Compare
Something-Something V2 (1 row) MAGVIT MAGVIT: Masked Generative Video Transformer code Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
Sprites (1 row) MGP-VAE (with geodesic loss) Disentangling Multiple Features in Video Sequences using Gaussian... code — Compare
YouTube-8M (1 row) SDCNet SDC-Net: Video prediction using spatially-displaced convolution 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. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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

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

Subtasks archive 2025-07-28

2 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 394 · with a code link: 208 · where Syntology ran a sample: 62 (58 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (62 of 394 tagged: 58 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument)

Page 1 of 4: papers 1 to 100 of 394, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 44 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; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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