Research map / 3D vision / Gaussian splatting
SplineGS: Learning Smooth Trajectories in Gaussian Splatting for Dynamic Scene Reconstruction
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes SplineGS, a dynamic-scene reconstruction method that models Gaussian trajectories with motion-adaptive spline functions on top of 3D Gaussian Splatting.
Problem
Novel view synthesis of scenes with deforming objects; existing 3D Gaussian Splatting deformation modules lack appropriate spatiotemporal inductive biases, producing unsmooth motion.
Approach
Represents each Gaussian's trajectory as a smooth spline with motion-adaptive control points, so that deformation is constrained to be temporally smooth rather than arbitrary per-frame offsets.
Experimental setup
Builds on: 3D Gaussian Splatting
Closest papers by meaning
- MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.92)
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction (CVPR 2024 · similarity 0.91)
- SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video (CVPR 2025 · similarity 0.91)
- Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation (AAAI 2025 · similarity 0.91)
- DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos (NeurIPS 2025 · similarity 0.90)
- Gaussian Splatting Lucas-Kanade (ICLR 2025 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.