Multi-Resolution Real-Time Deep Pose-Space Deformation
Open accessThe DOI matches its Crossref record; 52 of the 52 references it cites were found in a registry or an index.
Abstract
We present a hard-real-time multi-resolution mesh shape deformation technique for skeleton-driven soft-body characters. Producing mesh deformations at multiple levels of detail is very important in many applications in computer graphics. Our work targets applications where the multi-resolution shapes must be generated at fast speeds ("hard-real-time", e.g., a few milliseconds at most and preferably under 1 millisecond), as commonly needed in computer games, virtual reality and Metaverse applications. We assume that the character mesh is driven by a skeleton, and that high-quality character shapes are available in a set of training poses originating from a high-quality (slow) rig such as volumetric FEM simulation. Our method combines multi-resolution analysis, mesh partition of unity, and neural networks, to learn the pre-skinning shape deformations in an arbitrary character pose. Combined with linear blend skinning, this makes it possible to reconstruct the training shapes, as well as interpolate and extrapolate them. Crucially, we simultaneously achieve this at hard real-time rates and at multiple mesh resolution levels. Our technique makes it possible to trade deformation quality for memory and computation speed, to accommodate the strict requirements of modern real-time systems. Furthermore, we propose memory layout and code improvements to boost computation speeds. Previous methods for realtime approximations of quality shape deformations did not focus on hard real-time, or did not investigate the multi-resolution aspect of the problem. Compared to a "naive" approach of separately processing each hierarchical level of detail, our method offers a substantial memory reduction as well as computational speedups. It also makes it possible to construct the shape progressively level by level and interrupt the computation at any time, enabling graceful degradation of the deformation detail. We demonstrate our technique on several examples, including a stylized human character, human hands, and an inverse-kinematics-driven quadruped animal.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
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
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., & J, B. M. (2015) · ACM Transactions on Graphics · doi:10.1145/2816795.2818013 · Cited by 3,734
Surface simplification using quadric error metrics
Garland, M., & Heckbert, P. S. (1997) · Proceedings of the 24th annual conference on Computer graphics and interactive techniques - SIGGRAPH '97 · doi:10.1145/258734.258849 · Cited by 3,412
Hoppe, H. (1996) · Proceedings of the 23rd annual conference on Computer graphics and interactive techniques · doi:10.1145/237170.237216 · Cited by 2,817
(2003) · Computer Graphics Forum · doi:10.1111/1467-8659.00652 · Cited by 1,436
Pose space deformation: a unified approach to shape interpolation and skeleton-driven deformation
Lewis, J. P., Cordner, M., & Fong, N. (2000) · Proceedings of the 27th annual conference on Computer graphics and interactive techniques - SIGGRAPH '00 · doi:10.1145/344779.344862 · Cited by 853
Special Finite Element Methods for a Class of Second Order Elliptic Problems with Rough Coefficients
Babuška, I., Caloz, G., & Osborn, J. E. (1994) · SIAM Journal on Numerical Analysis · doi:10.1137/0731051 · Cited by 661 · cited 1×
“Partitions of unity are of course not new, see, e.g. [Babuška et al. 1994; Ohtake et al. 2003]; our contribution is to combine them with neural networks and a multi-resolution scheme.”
Funkhouser, T. A., & Séquin, C. H. (1993) · Proceedings of the 20th annual conference on Computer graphics and interactive techniques · doi:10.1145/166117.166149 · Cited by 603
Geometric skinning with approximate dual quaternion blending
Kavan, L., Collins, S., Žára, J., & O'Sullivan, C. (2008) · ACM Transactions on Graphics · doi:10.1145/1409625.1409627 · Cited by 385 · cited 2×
“In Figure 15, we compare our technique to Dual Quaternion Skin-ning [Kavan et al. 2008].”
Research works printed but not linked: 6
- Binh Huy Le and Zhigang Deng. 2014. Robust and accurate skeletal rigging from mesh sequences. ACM Trans. on Graphics (SIGGRAPH 2014) 33, 4 (2014), 1--10.
- Binh Huy Le and John-Peter Lewis. 2019. Direct delta mush skinning and variants. ACM Trans. on Graphics (SIGGRAPH 2019) 38, 4 (2019), 113--1.
- Peizhuo Li, Kfir Aberman, Rana Hanocka, Libin Liu, Olga Sorkine-Hornung, and Baoquan Chen. 2021. Learning skeletal articulations with neural blend shapes. ACM Trans. on Graphics (SIGGRAPH 2021) 40, 4 (2021), 1--15.
- Miguel A. Otaduy. 2004. 6-DoF Haptic Rendering Using Contact Levels of Detail and Haptic Textures. Ph. D. Dissertation. Department of Comp. Science, University of North Carolina at Chapel Hill.
- Hongyi Xu and Jernej Barbič. 2014. Signed Distance Fields for Polygon Soup Meshes. Graphics Interface 2014 (2014).
- Zhan Xu, Yang Zhou, Evangelos Kalogerakis, Chris Landreth, and Karan Singh. 2020. Rignet: Neural rigging for articulated characters. ACM Trans. on Graphics (SIGGRAPH 2020) 39, 4 (2020), 14.
Cited by
Self-supervised Learning of Latent Space Dynamics
Li, Y., Lin, G. W.-C., Larionov, E., et al. (2025) · Proceedings of the ACM on Computer Graphics and Interactive Techniques · doi:10.1145/3747854 · Cited by 3
“…et al. 2019; Li et al. 2023], deformable bodies [Barbič and James 2005; Chen et al. 2023; Harmon and Zorin 2013; Wang et al. 2015; Wu et al. 2015; Zheng and Barbic 2024], animated characters [Barbič et al. 2009, 2012; Jacobson et al. 2012] and fluids [Kim and Delaney 2013; Treuille et al. 2006].”
Metadata
- Authors
- Zheng, M., & Barbic, J.
- Affiliations
- University of Southern California (US)
- University of Southern California, Los Angeles, United States of America
- Venue
- ACM Transactions on Graphics
- Published
- 2024-11-19
- Volume
- 43
- Issue
- 6
- Pages
- 1-11
- ISSN
- 0730-0301 (ISSN-L)
- 1557-7368
- OpenAlex
- W4404527030
- Cited by
- 1
- References
- 18
- Citations by year
- 2025: 1
- FWCI
- 0.20
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM Transactions on Graphics (publishedVersion, cc-by)
- Funders
- National Science Foundation (IIS-1911224)
- Topics
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › 3D Shape Modeling and Analysis
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Computer Graphics and Visualization Techniques
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Human Motion and Animation
- Keywords
- linear blend skinning, partition of unity, artificial neural networks, memory reduction, inverse kinematics
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.
A second model labelled each claim on 2026-10-29 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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: Multi-Resolution Real-Time Deep Pose-Space Deformation. https://app.cochat.ai/papers/10.1145/3687985
- The paper
- Zheng, M., & Barbic, J. (2024). Multi-Resolution Real-Time Deep Pose-Space Deformation. ACM Transactions on Graphics. https://doi.org/10.1145/3687985
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.