Stochastic Liquid Deformation Fields: An SDE Generalisation of Closed-Form Continuous-Time Cells for Dynamic 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2608.28702v1
• Date: Thu, 27 Aug 2026 16:25:13 GMT
• Title: Stochastic Liquid Deformation Fields: An SDE Generalisation of Closed-Form Continuous-Time Cells for Dynamic 3D Gaussian Splatting
• Abstract summary: 3D Gaussian Splatting (D-3DGS) reconstructs dynamic scenes by deforming a canonical set of 3D Gaussians through a deformation field of frame time.<n>The noise is used only during training, needs no solver, and reduces exactly the deterministic field when switched off.<n>On the synthetic D-NeRF scenes the field is on par with the deterministic CfC and beats the baseline on most scenes; on the real-world NeRF-DS scenes the deterministic limit is already best and adding noise does not help.
• Score: 4.687898838871813
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deformable 3D Gaussian Splatting (D-3DGS) reconstructs dynamic scenes by deforming a canonical set of 3D Gaussians through a deformation field of frame time. Replacing its MLP with a stack of Closed-form Continuous-time (CfC) cells-a Liquid Neural Network that solves the Liquid Timeconstant ODE in closed form-gives the field continuous-time behaviour at feed-forward cost. That closed form, however, is only the deterministic limit of a noise-driven system, and drops the stochastic term usually credited for the robustness of liquid networks. We put it back: a small Gaussian perturbation is added to the time gate of every CfC cell, turning the deterministic field into a simple stochastic (SDE) one. The noise is used only during training, needs no solver, and reduces exactly to the CfC when switched off. On the synthetic D-NeRF scenes the stochastic field is on par with the deterministic CfC and beats the MLP baseline on most scenes; on the real-world NeRF-DS scenes the deterministic limit is already best and adding noise does not help. The study thus gives both a clean way to read the CfC field as an SDE and an honest account of when a plain noise term helps and when it does not.

Related papers

• LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction [59.32834240526981]
  Flow-based generative models are typically sampled by solving a deterministic ordinary differential equation (ODE)<n>Existing GRPO methods for flow models replace the Euler-time ODE with aotropic differential equation (SDE) during training.<n>We introduce LC-GRPO, a flow-based GRPO framework with Langevin correction targeting the marginal distribution at the resulting timestep.
  arXiv  Detail & Related papers  (2026-08-06T04:47:57Z)
• Same Loss, Same Noise, Opposite Schedules: Noise Structure and Optimizer Normalization Jointly Determine Whether Learning-Rate Cooldown Helps [4.422349568747053]
  We study the phase of a warmup-stable-decay (WSD) learning-rate schedule, now a default in large-model pretraining.<n>We give a provable account of which case obtains robustness, and it turns on two properties together: the structure of the gradient noise and whether the structure of the gradient noise normalizes its update.
  arXiv  Detail & Related papers  (2026-07-14T05:21:38Z)
• Liquid Neural Networks as a Drop-in Continuous-Time Deformation Field for Dynamic 3D Gaussian Splatting [4.1711003960475495]
  Deformable 3D Gaussian Splatting (D-3DGS) re-constructs dynamic scenes from monocular video by deforming a canonical set of 3Ds through a positional-encoded Gaussian of frame time t.<n>We optimisation the deformation field as a stack of Closed-form Continuous-time cells, a Liquid Neural Network (LNN)<n>The result is a near-zero-friction architectural design that turns the discrete deformation field into an explicit continuous-time function of t.
  arXiv  Detail & Related papers  (2026-06-04T08:43:44Z)
• Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics [92.39053980710702]
  Gradient Descent (SGD) is commonly modeled as a Langevin process, assuming that minibatch noise acts as Brownian motion.<n>This approximation relies on a continuous-time limit and a sqrt(eta) noise scaling that does not match the discrete SGD update at finite learning rate.<n>We propose an alternative formulation of SGD as deterministic dynamics in a fluctuating loss landscape induced by minibatch sampling.
  arXiv  Detail & Related papers  (2026-05-21T15:50:40Z)
• Recovering Physical Dynamics from Discrete Observations via Intrinsic Differential Consistency [12.266189649117003]
  We replace local supervision with a global structural constraint.<n>We train a time-conditioned secant velocity field whose deviation from this property serves two purposes.<n>As a training regularizer, it confines the hypothesis space to flows that compose consistently across temporal scales.
  arXiv  Detail & Related papers  (2026-05-08T20:24:32Z)
• A Stability-Aware Frozen Euler Autoencoder for Physics-Informed Tracking in Continuum Mechanics (SAFE-PIT-CM) [0.0]
  We introduce SAFE-PIT-CM, a Stability-Aware Frozen Euler autoencoder for Physics-Informed Tracking in Continuum Mechanics.<n>The architecture embeds a frozen, differentiable PDE solver inside an autoencoder.<n>The model also supports test-time training (TTT): learning alpha from a single simulation with no pre-training, using only the physics loss as supervision.
  arXiv  Detail & Related papers  (2026-02-27T12:13:43Z)
• Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting [79.37674445572462]
  Time series forecasting (TSF) remains a challenging problem due to the intricate entanglement of intraperiod-fluctuations and interperiod-trends.<n>Treating reshaped tensors as static images results in a topological mismatch.<n> relying on uniform fixed-size representations allocates modeling capacity inefficiently.<n>TimeGS is a novel framework that fundamentally shifts the forecasting paradigm from regression to 2D generative rendering.
  arXiv  Detail & Related papers  (2026-02-10T14:13:36Z)
• Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions [23.147474211347856]
  We introduce Neural Flows (NSFs) and their latent variants, which directly learn (latent) SDE transition laws.<n>Experiments on synthetic SDE simulations and on real-world tracking and video data show that NSFs maintain distributional accuracy comparable to numerical approaches.
  arXiv  Detail & Related papers  (2025-10-29T17:59:06Z)
• 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)
• Trajectory Flow Matching with Applications to Clinical Time Series Modeling [77.58277281319253]
  Trajectory Flow Matching (TFM) trains a Neural SDE in a simulation-free manner, bypassing backpropagation through the dynamics.<n>We demonstrate improved performance on three clinical time series datasets in terms of absolute performance and uncertainty prediction.
  arXiv  Detail & Related papers  (2024-10-28T15:54:50Z)
• Coarse Graining with Neural Operators for Simulating Chaotic Systems [78.64101336150419]
  Predicting the long-term behavior of chaotic systems is crucial for various applications such as climate modeling.<n>An alternative approach to such a full-resolved simulation is using a coarse grid and then correcting its errors through a temporalittext model.<n>We propose an alternative end-to-end learning approach using a physics-informed neural operator (PINO) that overcomes this limitation.
  arXiv  Detail & Related papers  (2024-08-09T17:05:45Z)
• Score-based Diffusion Models in Function Space [137.70916238028306]
  Diffusion models have recently emerged as a powerful framework for generative modeling.<n>This work introduces a mathematically rigorous framework called Denoising Diffusion Operators (DDOs) for training diffusion models in function space.<n>We show that the corresponding discretized algorithm generates accurate samples at a fixed cost independent of the data resolution.
  arXiv  Detail & Related papers  (2023-02-14T23:50:53Z)

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.