Papers › Scalable Neural Video Representations with Learnable Positional Features

Scalable Neural Video Representations with Learnable Positional Features

13 Oct 2022arXiv:2210.06823archive 2025-07-28

Subin Kim, Sihyun Yu, Jaeho Lee, Jinwoo Shin

Succinct representation of complex signals using coordinate-based neural representations (CNRs) has seen great progress, and several recent efforts focus on extending them for handling videos. Here, the main challenge is how to (a) alleviate a compute-inefficiency in training CNRs to (b) achieve high-quality video encoding while (c) maintaining the parameter-efficiency. To meet all requirements (a), (b), and (c) simultaneously, we propose neural video representations with learnable positional features (NVP), a novel CNR by introducing "learnable positional features" that effectively amortize a video as latent codes. Specifically, we first present a CNR architecture based on designing 2D latent keyframes to learn the common video contents across each spatio-temporal axis, which dramatically improves all of those three requirements. Then, we propose to utilize existing powerful image and video codecs as a compute-/memory-efficient compression procedure of latent codes. We demonstrate the superiority of NVP on the popular UVG benchmark; compared with prior arts, NVP not only trains 2 times faster (less than 5 minutes) but also exceeds their encoding quality as 34.07→34.57 (measured with the PSNR metric), even using $>$8 times fewer parameters. We also show intriguing properties of NVP, e.g., video inpainting, video frame interpolation, etc.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2210.06823")

Code

Syntology Ran 7 of 12 code samples harvested from 2 repositories linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 2 ran · our draft was wrong; 2 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 5 samples from 1 repository, 3 ran; community: 3 samples from 1 repository, 3 ran; 4 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

subin-kim-cv/NVP officialmentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 7 ran; 1 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
2ran · fixture could not drive it
1ran
5unverified

Licence: 7 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

cast_tuple subin-kim-cv/NVP/modulation.py official repository ran · honoured contract fingerprinted MIT (permissive) · 7bd1641f670e602d · report
exists subin-kim-cv/NVP/modulation.py official repository ran · violated contract MIT (permissive) · aa5486a3650902d8 · report
get_n_params subin-kim-cv/NVP/utils.py official repository ran MIT (permissive) · c6acd3e400fc2676 · report
get_mgrid subin-kim-cv/NVP/dataio.py official repository unverified MIT (permissive) · 18d43489e3fd0859 · report
image_mse subin-kim-cv/NVP/loss_functions.py official repository unverified MIT (permissive) · 196981f676d3a9d8 · report
ActivationLayer haochen-rye/nerv/model_nerv.py community ran · our draft was wrong no licence file found · pointer only · 878fd412e7a78234 · report
MLP haochen-rye/nerv/model_nerv.py community ran · fixture could not drive it no licence file found · pointer only · 4b4bad794e3e1cab · report
NormLayer haochen-rye/nerv/model_nerv.py community ran · our draft was wrong no licence file found · pointer only · 853ab1b19577355a · report
MLP identical code first harvested elsewhere ran · fixture could not drive it licence of this copy not recorded · a44ae0bc9c98e926 · report
ActivationLayer identical code first harvested elsewhere unverified licence of this copy not recorded · bab299b09f52a8de · report
NormLayer identical code first harvested elsewhere unverified licence of this copy not recorded · a764487191cdbab5 · report
evaluate identical code first harvested elsewhere unverified licence of this copy not recorded · 4bcdec64794c3fab · report

Tasks

Video CompressionVideo Frame InterpolationVideo InpaintingVideo Super-Resolution

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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