CoChat

Motion Representations for Articulated Animation

Open access
Siarohin, Aliaksandr, Woodford, Oliver J., Ren, Jian, Chai, Menglei, Tulyakov, Sergey · 2021 · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by 245

The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.

Abstract

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 model1can 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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr46437.2021.01344

Cites

15 of 15 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 23

  1. wiles, 2018, X2face: A network for controlling face generation using images, audio, and pose codes, Proceedings of the European Conference on Computer Vision
  2. 10.1109/CVPR.2018.00740 · DOI
  3. 10.1145/2929464.2929475 · DOI · Paper page
  4. tang, 2018, Dual generator generative adversarial networks for multi-domain image-to-image translation, ACCV
  5. 10.1109/CVPR.2018.00359 · DOI · Paper page
  6. wang, 2019, Few-shot video-to-video synthesis, Proceedings of the Neural Information Processing Systems Conference
  7. 10.1007/0-306-47815-3_5 · DOI · Paper page
  8. 10.1109/CVPR.2019.01005 · DOI · Paper page
  9. 10.1109/CVPR.2019.00096 · DOI
  10. 10.1145/3197517.3201283 · DOI · Paper page
  11. kim, 2019, Unsupervised keypoint learning for guiding class-conditional video prediction, Proceedings of the Neural Information Processing Systems Conference
  12. 10.1109/ICCV.2019.00600 · DOI · Paper page
  13. 10.1109/CVPR.2019.01121 · DOI · Paper page
  14. 10.1109/CVPR.2019.00248 · DOI · Paper page
  15. 10.1145/2601097.2601204 · DOI · Paper page
  16. siarohin, 2020, Motion-supervised co-part segmentation, Proceedings of the International Conference on Pattern Recognition
  17. 10.1109/CVPR.1997.609439 · DOI · Paper page
  18. bansal, 2018, Recycle-gan: Unsupervised video retargeting, Proceedings of the European Conference on Computer Vision
  19. 10.1145/3272127.3275075 · DOI · Paper page
  20. 10.1109/ICCV.2019.01013 · DOI · Paper page
  21. pumarola, 2018, Ganimation: Anatomically-aware facial animation from a single image, Proceedings of the European Conference on Computer Vision
  22. 10.1109/ICCV.2017.308 · DOI · Paper page
  23. ren, 2020, Human motion transfer from poses in the wild, 10.1007/978-3-030-67070-2_16 · DOI

Cited by

See all 245

Metadata

Authors
Siarohin, A., Woodford, O. J., Ren, J., Chai, M., & Tulyakov, S.
Venue
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2021-06
Pages
13648-13657
ISSN
1063-6919 (ISSN-L)
OpenAlex
W3132524019
Cited by
245
References
15
FWCI
12.91
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.