4D Gaussian Splatting as a Learned Dynamical System

• URL: http://arxiv.org/abs/2512.19648v1
• Date: Mon, 22 Dec 2025 18:20:29 GMT
• Title: 4D Gaussian Splatting as a Learned Dynamical System
• Authors: Arnold Caleb Asiimwe, Carl Vondrick,
• Abstract summary: EvoGS treats the Gaussian representation as an evolving physical system whose state evolves continuously under a learned motion law.<n> Experiments on dynamic scene benchmarks show that EvoGS achieves better motion coherence and temporal consistency compared to deformation-field baselines.
• Score: 41.36168012923513
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We reinterpret 4D Gaussian Splatting as a continuous-time dynamical system, where scene motion arises from integrating a learned neural dynamical field rather than applying per-frame deformations. This formulation, which we call EvoGS, treats the Gaussian representation as an evolving physical system whose state evolves continuously under a learned motion law. This unlocks capabilities absent in deformation-based approaches:(1) sample-efficient learning from sparse temporal supervision by modeling the underlying motion law; (2) temporal extrapolation enabling forward and backward prediction beyond observed time ranges; and (3) compositional dynamics that allow localized dynamics injection for controllable scene synthesis. Experiments on dynamic scene benchmarks show that EvoGS achieves better motion coherence and temporal consistency compared to deformation-field baselines while maintaining real-time rendering

Related papers

• FLAG-4D: Flow-Guided Local-Global Dual-Deformation Model for 4D Reconstruction [7.144085821875197]
  FLAG-4D reconstructs how 3D Gaussian primitives evolve through space and time.<n>It achieves higher-fidelity and more temporally coherent reconstructions with finer detail than state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-02-09T11:55:15Z)
• Schrödinger-Inspired Time-Evolution for 4D Deformation Forecasting [3.0519975190807407]
  We propose a physics-guided neural architecture that embeds an explicit time-evolution operator within a deep convolutional framework for 4D prediction.<n>We demonstrate accurate and stable prediction of future 4D states, including intensities deformation and fields, on synthetic benchmarks.
  arXiv  Detail & Related papers  (2026-01-31T11:17:04Z)
• VDEGaussian: Video Diffusion Enhanced 4D Gaussian Splatting for Dynamic Urban Scenes Modeling [68.65587507038539]
  We present a novel video diffusion-enhanced 4D Gaussian Splatting framework for dynamic urban scene modeling.<n>Our key insight is to distill robust, temporally consistent priors from a test-time adapted video diffusion model.<n>Our method significantly enhances dynamic modeling, especially for fast-moving objects, achieving an approximate PSNR gain of 2 dB.
  arXiv  Detail & Related papers  (2025-08-04T07:24:05Z)
• ODE-GS: Latent ODEs for Dynamic Scene Extrapolation with 3D Gaussian Splatting [13.520967762833408]
  We introduce ODE-GS, a novel approach that integrates 3D Gaussian Splatting with latent neural ordinary differential equations (ODEs)<n>Our approach first learns an model to generate accurate Gaussian trajectories within the observed window, then trains a Transformer encoder to aggregate past trajectories into a latent state evolved via a neural ODE.<n> numerical integration produces smooth, physically plausible future Gaussian trajectories, enabling rendering at arbitrary future timestamps.
  arXiv  Detail & Related papers  (2025-06-05T18:02:30Z)
• STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering [15.873329633980015]
  Existing 3DGS-based methods for dynamic reconstruction often suffer from textbfSTDR (Spatio-coupling DeTemporal for Real-time rendering)<n>We propose textbfSTDR (Spatio-coupling DeTemporal for Real-time rendering), a plug-and-play module learns thattemporal probability distributions for each scene.
  arXiv  Detail & Related papers  (2025-05-28T14:26:41Z)
• ParticleGS: Particle-Based Dynamics Modeling of 3D Gaussians for Prior-free Motion Extrapolation [9.59448024784555]
  We propose a novel dynamic 3D Gaussian Splatting prior-free motion extrapolation framework based on particle dynamics systems.<n>Instead of simply fitting to the observed visual frame sequence, we aim to more effectively model the gaussian particle dynamics system.<n> Experimental results demonstrate that the proposed method achieves comparable rendering quality with existing approaches in reconstruction tasks.
  arXiv  Detail & Related papers  (2025-05-26T17:46:35Z)
• CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving [12.006435326659526]
  We introduce a novel 4D Gaussian Splatting (4DGS) approach to improve dynamic scene rendering.<n> Specifically, we employ a 2D semantic segmentation foundation model to self-supervise the 4D semantic features of Gaussians.<n>By aggregating and encoding both semantic and temporal deformation features, each Gaussian is equipped with cues for potential deformation compensation.
  arXiv  Detail & Related papers  (2025-03-09T19:58:51Z)
• UrbanGS: Semantic-Guided Gaussian Splatting for Urban Scene Reconstruction [86.4386398262018]
  UrbanGS uses 2D semantic maps and an existing dynamic Gaussian approach to distinguish static objects from the scene.<n>For potentially dynamic objects, we aggregate temporal information using learnable time embeddings.<n>Our approach outperforms state-of-the-art methods in reconstruction quality and efficiency.
  arXiv  Detail & Related papers  (2024-12-04T16:59:49Z)
• Gaussian Splatting Lucas-Kanade [0.11249583407496218]
  We propose a novel analytical approach that adapts the classical Lucas-Kanade method to dynamic Gaussian splatting.<n>By leveraging the intrinsic properties of the forward warp field network, we derive an analytical velocity field that, through time integration, facilitates accurate scene flow computation.<n>Our method excels in reconstructing highly dynamic scenes with minimal camera movement, as demonstrated through experiments on both synthetic and real-world scenes.
  arXiv  Detail & Related papers  (2024-07-16T01:50:43Z)
• Equivariant Graph Neural Operator for Modeling 3D Dynamics [148.98826858078556]
  We propose Equivariant Graph Neural Operator (EGNO) to directly models dynamics as trajectories instead of just next-step prediction. EGNO explicitly learns the temporal evolution of 3D dynamics where we formulate the dynamics as a function over time and learn neural operators to approximate it. Comprehensive experiments in multiple domains, including particle simulations, human motion capture, and molecular dynamics, demonstrate the significantly superior performance of EGNO against existing methods.
  arXiv  Detail & Related papers  (2024-01-19T21:50:32Z)
• SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes [59.23385953161328]
  Novel view synthesis for dynamic scenes is still a challenging problem in computer vision and graphics. We propose a new representation that explicitly decomposes the motion and appearance of dynamic scenes into sparse control points and dense Gaussians. Our method can enable user-controlled motion editing while retaining high-fidelity appearances.
  arXiv  Detail & Related papers  (2023-12-04T11:57:14Z)
• Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering [49.36767999382054]
  We present a unified representation model, called Periodic Vibration Gaussian (PVG)<n>PVG builds upon the efficient 3D Gaussian splatting technique, originally designed for static scene representation.<n>PVG exhibits 900-fold acceleration in rendering over the best alternative.
  arXiv  Detail & Related papers  (2023-11-30T13:53:50Z)
• Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis [58.5779956899918]
  We present a method that simultaneously addresses the tasks of dynamic scene novel-view synthesis and six degree-of-freedom (6-DOF) tracking of all dense scene elements. We follow an analysis-by-synthesis framework, inspired by recent work that models scenes as a collection of 3D Gaussians. We demonstrate a large number of downstream applications enabled by our representation, including first-person view synthesis, dynamic compositional scene synthesis, and 4D video editing.
  arXiv  Detail & Related papers  (2023-08-18T17:59:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.