Papers › Motion Representations for Articulated Animation

Motion Representations for Articulated Animation

22 Apr 2021CVPR 2021 1arXiv:2104.11280archive 2025-07-28

Aliaksandr Siarohin, Oliver J. Woodford, Jian Ren, Menglei Chai, Sergey Tulyakov

We propose novel motion representations for animating articulated objects consisting of distinct parts. In a completely unsupervised manner, our method identifies object parts, tracks them in a driving video, and infers their motions by considering their principal axes. In contrast to the previous keypoint-based works, our method extracts meaningful and consistent regions, describing locations, shape, and pose. The regions correspond to semantically relevant and distinct object parts, that are more easily detected in frames of the driving video. To force decoupling of foreground from background, we model non-object related global motion with an additional affine transformation. To facilitate animation and prevent the leakage of the shape of the driving object, we disentangle shape and pose of objects in the region space. Our model can animate a variety of objects, surpassing previous methods by a large margin on existing benchmarks. We present a challenging new benchmark with high-resolution videos and show that the improvement is particularly pronounced when articulated objects are considered, reaching 96.6% user preference vs. the state of the art.

PaperPDFConference PDFCodeCode 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="2104.11280")

Code

Syntology Ran 2 of 6 code samples harvested from 2 repositories linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 5 samples from 1 repository, 2 ran; community (archive-listed): 1 sample from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

snap-research/articulated-animation officialmentioned in papermentioned on GitHubpytorch report
AliaksandrSiarohin/first-order-model mentioned on GitHubpytorch 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

6 samples harvested; 2 ran; 0 honoured the contract we drafted; 4 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 · fixture could not drive it
1ran
4unverified

Licence: 5 of the 6 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. “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.

Hourglass snap-research/articulated-animation/modules/region_predictor.py official repository ran licence not identified · pointer only · 0f297bc88d95e3b0 · report
svd snap-research/articulated-animation/modules/region_predictor.py official repository ran · fixture could not drive it fingerprinted licence not identified · pointer only · 0d236fe33ec308ac · report
AntiAliasInterpolation2d snap-research/articulated-animation/modules/region_predictor.py official repository unverified licence not identified · pointer only · 9ea00b3a056c3e42 · report
Decoder snap-research/articulated-animation/modules/region_predictor.py official repository unverified licence not identified · pointer only · 5e2e6d30631114c2 · report
RegionPredictor snap-research/articulated-animation/modules/region_predictor.py official repository unverified licence not identified · pointer only · 0b353848134c5944 · report
KPDetector AliaksandrSiarohin/first-order-model/modules/keypoint_detector.py community (archive-listed) unverified MIT (permissive) · b31dd89f51305594 · report

Tasks

ObjectVideo Reconstruction

Datasets

Introduced by this paper, per the archive.

TED-talks

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Reconstruction MGif Siarohin et al. L1 0.0206 #1 of 2 Archive leaderboard report
Video Reconstruction MGif FOMM L1 0.0223 #2 of 2 Archive leaderboard report
Video Reconstruction TED-talks Siarohin et al. AED 0.114 #1 of 2 Archive leaderboard report
Video Reconstruction TED-talks Siarohin et al. AKD 3.75 #1 of 2 Archive leaderboard report
Video Reconstruction TED-talks Siarohin et al. L1 0.026 #1 of 2 Archive leaderboard report
Video Reconstruction TED-talks Siarohin et al. MKR 0.007 #1 of 2 Archive leaderboard report
Video Reconstruction TED-talks FOMM AED 0.163 #2 of 2 Archive leaderboard report
Video Reconstruction TED-talks FOMM AKD 7.07 #2 of 2 Archive leaderboard report
Video Reconstruction TED-talks FOMM L1 0.033 #2 of 2 Archive leaderboard report
Video Reconstruction TED-talks FOMM MKR 0.014 #2 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (256) Siarohin et al. AED 0.152 #1 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (256) Siarohin et al. AKD 5.58 #1 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (256) Siarohin et al. L1 0.047 #1 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (256) Siarohin et al. MKR 0.027 #1 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (256) FOMM AED 0.172 #2 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (256) FOMM AKD 6.53 #2 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (256) FOMM L1 0.056 #2 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (256) FOMM MKR 0.033 #2 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (512) Siarohin et al. AED 0.172 #1 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (512) Siarohin et al. AKD 13.86 #1 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (512) Siarohin et al. L1 0.064 #1 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (512) Siarohin et al. MKR 0.043 #1 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (512) FOMM AED 0.203 #2 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (512) FOMM AKD 17.12 #2 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (512) FOMM L1 0.075 #2 of 2 Archive leaderboard report
Video Reconstruction Tai-Chi-HD (512) FOMM MKR 0.066 #2 of 2 Archive leaderboard report
Video Reconstruction VoxCeleb Siarohin et al. AED 0.133 #1 of 2 Archive leaderboard report
Video Reconstruction VoxCeleb Siarohin et al. AKD 1.28 #1 of 2 Archive leaderboard report
Video Reconstruction VoxCeleb Siarohin et al. L1 0.040 #1 of 2 Archive leaderboard report
Video Reconstruction VoxCeleb FOMM AED 0.134 #2 of 2 Archive leaderboard report
Video Reconstruction VoxCeleb FOMM AKD 1.27 #2 of 2 Archive leaderboard report
Video Reconstruction VoxCeleb FOMM L1 0.041 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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