Pith. sign in

REVIEW 8 cited by

SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.14937 v3 pith:WJ7ZI6ZQ submitted 2023-12-04 cs.CV cs.GR

Yi-Hua Huang , Yang-Tian Sun , Ziyi Yang , Xiaoyang Lyu , Yan-Pei Cao , Xiaojuan Qi This is my paper
classification cs.CVcs.GR
keywords motioncontrolscenesgaussiansnovelpointsappearancedynamic
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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. Project page: https://yihua7.github.io/SC-GS-web/

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    GS-STVSR achieves state-of-the-art continuous spatio-temporal video super-resolution quality with nearly constant inference time at standard scales and over 3x speedup at extreme scales using 2D Gaussian Splatting.

  2. GSDeformer: Direct, Real-time and Extensible Cage-based Deformation for 3D Gaussian Splatting

    cs.CV 2024-05 unverdicted novelty 7.0 of 10

    GSDeformer enables direct, real-time cage-based deformation on 3D Gaussian Splatting via a proxy point-cloud representation and automated cage construction, without modifying the core 3DGS architecture.

  3. Learning Video Dynamics with Predictive Differentiable Rendering

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    PDR integrates a plug-and-play 2D Gaussian representation and CUDA renderer into pixel-based video predictors, replacing MSE loss with L1+SSIM to improve detail preservation on benchmarks like TaxiBJ and Human3.6M.

  4. PersistGS: Differentiable Physics for Object Permanence in 4D Gaussian Splatting

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    PersistGS decomposes scenes into per-object Gaussians and meshes, fits friction and velocity via differentiable simulation from pre-occlusion motion, and uses the resulting physics trajectory to position Gaussians dur...

  5. GaussiAnimate: Reconstruct and Rig Animatable Categories with Level of Dynamics

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    Skelebones compresses 4D Gaussian shapes into compact, controllable bones and skeletons, delivering 17.3% PSNR gains over LBS and 21.7% over BoB for unseen poses while preserving reconstruction quality.

  6. Leveraging 2D Priors and SDF Guidance for Dynamic Urban Scene Rendering

    cs.CV 2025-10 conditional novelty 5.0 of 10

    UGSDF achieves state-of-the-art novel-view rendering of dynamic urban objects without LiDAR or 3D motion annotations by jointly optimizing SDFs and 3D Gaussians under 2D depth and point-tracking priors.

  7. Beyond Static Gaussians: An Empirical Investigation of Architectural Paradigms for Dynamic 3D Scene Reconstruction

    cs.CV 2026-05 unverdicted novelty 4.0 of 10

    Structure-guided dynamic 3DGS methods deliver superior reconstruction fidelity and compactness on D-NeRF while gaussian-centric methods provide higher rendering speeds at the cost of quality variability and storage.

  8. Real-Time Physics Simulation with Dynamic Mesh-Gaussian Reconstructions

    cs.CV 2026-05 unverdicted novelty 4.0 of 10

    Dual-representation framework pairs fixed-topology meshes for physics with Gaussian splatting for rendering, but two conversion strategies from varying-topology reconstructions cause 65-80% geometric degradation and u...

Pith tools