SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Novel view synthesis for dynamic scenes is still a challenging problem in computer vision and graphics. Recently, Gaussian splatting has emerged as a robust technique to represent static scenes and enable high-quality and real-time novel view synthesis. Building upon this technique, we propose a new representation that explicitly decomposes the motion and appearance of dynamic scenes into sparse control points and dense Gaussians, respectively. Our key idea is to use sparse control points, significantly fewer in number than the Gaussians, to learn compact 6 DoF transformation bases, which can be locally interpolated through learned interpolation weights to yield the motion field of 3D Gaussians. We employ a deformation MLP to predict time-varying 6 DoF transformations for each control point, which reduces learning complexities, enhances learning abilities, and facilitates obtaining temporal and spatial coherent motion patterns. Then, we jointly learn the 3D Gaussians, the canonical space locations of control points, and the deformation MLP to reconstruct the appearance, geometry, and dynamics of 3D scenes. During learning, the location and number of control points are adaptively adjusted to accommodate varying motion complexities in different regions, and an ARAP loss following the principle of as rigid as possible is developed to enforce spatial continuity and local rigidity of learned motions. Finally, thanks to the explicit sparse motion representation and its decomposition from appearance, our method can enable user-controlled motion editing while retaining high-fidelity appearances. Extensive experiments demonstrate that our approach outperforms existing approaches on novel view synthesis with a high rendering speed and enables novel appearance-preserved motion editing applications.
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
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00068 · Cited by 14,623
NeRF: representing scenes as neural radiance fields for view synthesis
Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2022) · Communications of the ACM · doi:10.1145/3503250 · Cited by 6,852
Structure-from-Motion Revisited
Schonberger, J. L., & Frahm, J.-M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.445 · Cited by 6,433 · cited 1×
“D-NeRF datasets contain eight dynamic scenes with 360 ◦ viewpoint settings, and the NeRF-DS datasets consist of seven captured videos with camera pose estimated using colmap [39].”
3D Gaussian Splatting for Real-Time Radiance Field Rendering
Kerbl, B., Kopanas, G., Leimkuehler, T., & Drettakis, G. (2023) · ACM Transactions on Graphics · doi:10.1145/3592433 · Cited by 6,025
DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time
Newcombe, R. A., Fox, D., & Seitz, S. M. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298631 · Cited by 951 · cited 2×
“Then, the interpolation weights for control point p k can be com-3 puted with Gaussian-kernel RBF [4, 9, 32] as: where d jk is the distance between center of Gaussian G j and the neighboring control point p k , and o k is the learned radius parameter of p k .”
BackgroundMethodRobust single-view geometry and motion reconstruction
Li, H., Adams, B., Guibas, L. J., & Pauly, M. (2009) · ACM Transactions on Graphics · doi:10.1145/1618452.1618521 · Cited by 334
Neural point cloud rendering via multi-plane projection
Dai, P., Zhang, Y., Li, Z., Liu, S., & Zeng, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00785 · Cited by 80 · cited 1×
“Utilizing a point-based [2, 10, 14, 15, 46, 53, 67] scene representation, this method rasterizes 3D Gaussians to render images from specified views.”
Cited by
AniGen: Unified S 3 Fields for Animatable 3D Asset Generation
Huang, Y.-H., Zou, Z.-X., He, Y., Chang, C., Pu, C.-F., Yang, Z., Guo, Y.-C., Cao, Y.-P., & Qi, X. (2026) · ACM Transactions on Graphics · doi:10.1145/3811297
“SMRNet [Zhang et al. 2024a] and HMC [Wang et al. 2023a] animate existing 3D shapes by retargeting them with reference animations, while SC4D [Wu et al. 2024b] and Deform-Splat [Kim et al. 2025] optimize 3D shapes into dynamic motion with sparse control and local rigidity [Huang et al. 2024].”
Self-citation
Metadata
- Authors
- Huang, Y.-H., Sun, Y.-T., Yang, Z., Lyu, X., Cao, Y.-P., & Qi, X.
- Venue
- 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2024-06-16
- Pages
- 4220-4230
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4402715996
- Cited by
- 183
- References
- 7
- FWCI
- 52.55
- 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.