G3AN: Disentangling Appearance and Motion for Video Generation
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Creating realistic human videos entails the challenge of being able to simultaneously generate both appearance, as well as motion. To tackle this challenge, we introduce G3AN, a novel spatio-temporal generative model, which seeks to capture the distribution of high dimensional video data and to model appearance and motion in disentangled manner. The latter is achieved by decomposing appearance and motion in a three-stream Generator, where the main stream aims to model spatio-temporal consistency, whereas the two auxiliary streams augment the main stream with multi-scale appearance and motion features, respectively. An extensive quantitative and qualitative analysis shows that our model systematically and significantly outperforms state-of-the-art methods on the facial expression datasets MUG and UvA-NEMO, as well as the Weizmann and UCF101 datasets on human action. Additional analysis on the learned latent representations confirms the successful decomposition of appearance and motion.
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.
Integrity signals
Registry
Cites
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.
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · cited 1×
“Generative Adversarial Networks (GANs) [10] have witnessed increasing attention due to their ability to model complex data distributions, which allows them to generate realistic images [5, 17, 18, 21, 24, 25, 41, 44], as well as to translate images [2, 15, 29, 32].”
BackgroundGANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.08500 · Cited by 8,365
Large Scale GAN Training for High Fidelity Natural Image Synthesis
Brock, A., Donahue, J., & Simonyan, K. (2018) · arXiv · doi:10.48550/arxiv.1809.11096 · Cited by 3,717
Self-Attention Generative Adversarial Networks
Zhang, H., Goodfellow, I., Metaxas, D., & Odena, A. (2018) · arXiv · doi:10.48550/arxiv.1805.08318 · Cited by 3,353 · cited 2×
“Despite Self-Attention (SA) has been successfully applied in image generation within SAGAN [43], however it has not been explored in the context of spatio-temporal video generation yet.”
BackgroundAttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
Xu, T., Zhang, P., Huang, Q., Zhang, H., Gan, Z., Huang, X., & He, X. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00143 · Cited by 1,923
Bulat, A., & Tzimiropoulos, G. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.116 · Cited by 1,464 · cited 1×
“We crop faces in each frame based on detected landmarks using [6]2.”
MethodMoCoGAN: Decomposing Motion and Content for Video Generation
Tulyakov, S., Liu, M.-Y., Yang, X., & Kautz, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00165 · Cited by 1,076
Chan, C., Ginosar, S., Zhou, T., & Efros, A. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00603 · Cited by 737
Wang, T.-C., Liu, M.-Y., Zhu, J.-Y., Liu, G., Tao, A., Kautz, J., & Catanzaro, B. (2018) · arXiv · doi:10.48550/arxiv.1808.06601 · Cited by 594
Cited by
Align Your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
Blattmann, A., Rombach, R., Ling, H., Dockhorn, T., Kim, S. W., Fidler, S., & Kreis, K. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.02161 · Cited by 724
“[95] Yaohui Wang, Piotr Bilinski, Francois Bremond, and Antitza Dantcheva.”
BackgroundStyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2
Skorokhodov, I., Tulyakov, S., & Elhoseiny, M. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00361 · Cited by 199
Qu, B., Liang, X., Sun, S., & Gao, W. (2024) · arXiv · doi:10.48550/arxiv.2404.13573 · Cited by 44
Self-Supervised Video GANs: Learning for Appearance Consistency and Motion Coherency
Hyun, S., Kim, J., & Heo, J.-P. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01068 · Cited by 16
“Similarly, G(3)AN [38] proposes a three-stream generator to disentangle motion and appearance with a self-attention module for a spatio-temporal consistency of videos.”
BackgroundMethodInfluentialLaMD: Latent Motion Diffusion for Image-Conditional Video Generation
Hu, Y., Chen, Z., & Luo, C. (2023) · arXiv · doi:10.48550/arxiv.2304.11603 · Cited by 16
“Most of the existing methods focus on modeling the global motion representation from videos, i.e. by approaching a prior normal distribution to enable stochastic generation of videos from randomly sampled motion during inference [2,11,45,51,57].”
Metadata
- Authors
- Wang, Y., Bilinski, P., Bremond, F., & Dantcheva, A.
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 5263-5272
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3013175169
- Cited by
- 82
- References
- 11
- FWCI
- 4.14
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: G3AN: Disentangling Appearance and Motion for Video Generation. https://app.cochat.ai/papers/10.1109/cvpr42600.2020.00531
- The paper
- Wang, Y., Bilinski, P., Bremond, F., & Dantcheva, A. (2020). G3AN: Disentangling Appearance and Motion for Video Generation. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr42600.2020.00531
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.