ODE-GS: Latent ODEs for Dynamic Scene Extrapolation with 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2506.05480v1
• Date: Thu, 05 Jun 2025 18:02:30 GMT
• Title: ODE-GS: Latent ODEs for Dynamic Scene Extrapolation with 3D Gaussian Splatting
• Authors: Daniel Wang, Patrick Rim, Tian Tian, Alex Wong, Ganesh Sundaramoorthi,
• Abstract summary: ODE-GS is a novel method that unifies 3D Gaussian Splatting with latent neural ordinary differential equations (ODEs) to forecast dynamic 3D scenes.<n>Our results demonstrate that continuous-time latent dynamics are a powerful, practical route to prediction of complex 3D scenes.
• Score: 10.497667917243852
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present ODE-GS, a novel method that unifies 3D Gaussian Splatting with latent neural ordinary differential equations (ODEs) to forecast dynamic 3D scenes far beyond the time span seen during training. Existing neural rendering systems - whether NeRF- or 3DGS-based - embed time directly in a deformation network and therefore excel at interpolation but collapse when asked to predict the future, where timestamps are strictly out-of-distribution. ODE-GS eliminates this dependency: after learning a high-fidelity, time-conditioned deformation model for the training window, we freeze it and train a Transformer encoder that summarizes past Gaussian trajectories into a latent state whose continuous evolution is governed by a neural ODE. Numerical integration of this latent flow yields smooth, physically plausible Gaussian trajectories that can be queried at any future instant and rendered in real time. Coupled with a variational objective and a lightweight second-derivative regularizer, ODE-GS attains state-of-the-art extrapolation on D-NeRF and NVFI benchmarks, improving PSNR by up to 10 dB and halving perceptual error (LPIPS) relative to the strongest baselines. Our results demonstrate that continuous-time latent dynamics are a powerful, practical route to photorealistic prediction of complex 3D scenes.

Related papers

• Pseudo Depth Meets Gaussian: A Feed-forward RGB SLAM Baseline [64.42938561167402]
  We propose an online 3D reconstruction method using 3D Gaussian-based SLAM, combined with a feed-forward recurrent prediction module.<n>This approach replaces slow test-time optimization with fast network inference, significantly improving tracking speed.<n>Our method achieves performance on par with the state-of-the-art SplaTAM, while reducing tracking time by more than 90%.
  arXiv  Detail & Related papers  (2025-08-06T16:16:58Z)
• HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis [59.25751939710903]
  We propose a novel deformable Gaussian splatting framework that addresses embodied view synthesis from long monocular RGB videos.<n>Our method leverages invertible Gaussian Splatting deformation networks to reconstruct large-scale, dynamic environments accurately.<n>Results highlight a practical and scalable solution for EVS in real-world scenarios.
  arXiv  Detail & Related papers  (2025-06-24T03:54:40Z)
• Speedy Deformable 3D Gaussian Splatting: Fast Rendering and Compression of Dynamic Scenes [57.69608119350651]
  Recent extensions of 3D Gaussian Splatting (3DGS) to dynamic scenes achieve high-quality novel view synthesis by using neural networks to predict the time-varying deformation of each Gaussian.<n>However, performing per-Gaussian neural inference at every frame poses a significant bottleneck, limiting rendering speed and increasing memory and compute requirements.<n>We present Speedy Deformable 3D Gaussian Splatting (SpeeDe3DGS), a general pipeline for accelerating the rendering speed of dynamic 3DGS and 4DGS representations by reducing neural inference through two complementary techniques.
  arXiv  Detail & Related papers  (2025-06-09T16:30:48Z)
• FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction [64.30050475414947]
  FreeTimeGS is a novel 4D representation that allows Gaussian primitives to appear at arbitrary time and locations.<n>Our representation possesses the strong flexibility, thus improving the ability to model dynamic 3D scenes.<n> Experiments results on several datasets show that the rendering quality of our method outperforms recent methods by a large margin.
  arXiv  Detail & Related papers  (2025-06-05T17:59:57Z)
• Robust Moment Identification for Nonlinear PDEs via a Neural ODE Approach [7.097168937001958]
  We propose a data-driven framework for learning reduced-order moment dynamics from PDE-governed systems using Neural ODEs.<n>Using as an application platform the nonlinear Schr"odinger equation, the framework accurately recovers governing moment dynamics when closure is available.
  arXiv  Detail & Related papers  (2025-06-05T17:03:42Z)
• 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)
• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• TT-Occ: Test-Time Compute for Self-Supervised Occupancy via Spatio-Temporal Gaussian Splatting [32.57885385644153]
  Self-supervised 3D occupancy prediction offers a promising solution for understanding driving scenes without requiring costly 3D annotations.<n>We propose a practical and flexible test-time occupancy prediction framework termed TT-Occ.
  arXiv  Detail & Related papers  (2025-03-11T14:37:39Z)
• latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction [48.86083272054711]
  latentSplat is a method to predict semantic Gaussians in a 3D latent space that can be splatted and decoded by a light-weight generative 2D architecture. We show that latentSplat outperforms previous works in reconstruction quality and generalization, while being fast and scalable to high-resolution data.
  arXiv  Detail & Related papers  (2024-03-24T20:48:36Z)
• 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)
• Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle [9.082693946898733]
  We introduce a novel point-based approach for fast dynamic scene reconstruction and real-time rendering from both multi-view and monocular videos. In contrast to the prevalent NeRF-based approaches hampered by slow training and rendering speeds, our approach harnesses recent advancements in point-based 3D Gaussian Splatting (3DGS) Our proposed approach showcases a substantial efficiency improvement, achieving a $5times$ faster training speed compared to the per-frame 3DGS modeling.
  arXiv  Detail & Related papers  (2023-12-06T11:25:52Z)

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.