FLUIDSPLAT: Reconstructing Physical Fields from Sparse Sensors via Gaussian Primitives

• URL: http://arxiv.org/abs/2605.18866v1
• Date: Fri, 15 May 2026 09:10:02 GMT
• Title: FLUIDSPLAT: Reconstructing Physical Fields from Sparse Sensors via Gaussian Primitives
• Abstract summary: We introduce FLUIDSPLAT, a sensor-conditioned model that predicts K anisotropic Gaussian primitives forming a partition-of-unity scaffold.<n>On a standard cylinder-flow benchmark, FLUIDSPLAT achieves the best mean error across all surface-sensor layouts.
• Score: 31.072122193693854
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reconstructing continuous flow fields from sparse surface-mounted sensors is central to aerodynamic design, flow control, and digital-twin instrumentation. Existing neural methods for this task typically encode sensor readings into implicit latent codes with little spatial interpretability and limited formal guidance on how representational capacity should scale with observation count. Inspired by 3D Gaussian Splatting, we introduce FLUIDSPLAT, a sensor-conditioned model that predicts K anisotropic Gaussian primitives forming a partition-of-unity scaffold, a spatially explicit and interpretable intermediate representation of the flow. For an idealized Gaussian primitive estimator, we prove an $O(K^{-s/d})$ approximation rate for fields with Sobolev smoothness $s$; incorporating $N$ noisy observations yields a squared-risk decomposition with bias $O(K^{-2s/d})$ and variance $O(σ^{2}K/N)$.Balancing the two yields $K^{*}\!\sim\!(N/σ^{2})^{d/(2s+d)}$: primitive count cannot grow freely under sparse sensing, revealing a variance bottleneck that motivates complementing the scaffold with a state-conditioned residual decoder. On a standard cylinder-flow benchmark, FLUIDSPLAT achieves the best mean error across all surface-sensor layouts; on AirfRANS with 8 surface-pressure sensors, it reduces error by 11-23% over the strongest baseline across three standard splits.

Related papers

• Gaussian-JEPA: Joint-Embedding Predictive Learning for 3D Gaussian Splats [91.55220894541151]
  3D Gaussian Splatting (3DGS) represents 3D content with anisotropic primitives that jointly encode geometry and appearance.<n>We introduce Gaussian-JEPA, which predicts representations of held-out Gaussian token blocks from visible context.
  arXiv  Detail & Related papers  (2026-08-16T09:43:50Z)
• Level-Crossing Density as a Mesh-Free High-Frequency Auxiliary Loss for Implicit Neural Representations [0.0]
  We derive smooth Monte-Carlo estimators for a continuous neural field using no grid, no complex, no persistence.<n>The estimator is accurate to 1-3% against exact topology in 2D and 3D, and costs about 3 ms per iteration.<n>In 3D neural-SDF fitting, however, a failure mode we believe general to any sampled soft topology objective appears.
  arXiv  Detail & Related papers  (2026-07-07T04:23:23Z)
• GS^2: Graph-based Spatial Distribution Optimization for Compact 3D Gaussian Splatting [50.2045409672451]
  3D Gaussian Splatting (3DGS) has demonstrated breakthrough performance in novel view synthesis and real-time rendering.<n>It is constrained by the high memory cost due to a huge number of Gaussian points.<n>We propose graph-based spatial distribution optimization for compact 3DGS.
  arXiv  Detail & Related papers  (2026-04-02T10:41:51Z)
• F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting [28.800888081472422]
  We present F4Splat, which performs Feed-Forward predictive densification for Feed-Forward 3D Gaussian Splatting.<n>Our model predicts per-region densification scores to estimate the required Gaussian density and allows explicit control over the final Gaussian budget.<n>Experiments demonstrate that our model achieves superior novel-view synthesis performance compared to prior uncalibrated feed-forward methods.
  arXiv  Detail & Related papers  (2026-03-22T16:03:56Z)
• ReSplat: Learning Recurrent Gaussian Splats [98.14472247275512]
  ReSplat is a feed-forward recurrent Gaussian splatting model that iteratively refines 3D Gaussians without explicitly computing gradients.<n>We introduce a compact reconstruction model that operates in a $16 times$ subsampled space, producing $16 times$ fewer Gaussians than previous per-pixel Gaussian models.<n>Our method achieves state-of-the-art performance while significantly reducing the number of Gaussians and improving the rendering speed.
  arXiv  Detail & Related papers  (2025-10-09T17:59:59Z)
• GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flow [1.5129569747339653]
  Occupancy estimation has become a prominent task in 3D computer vision.<n>We present a novel approach to occupancy estimation, termed GaussianFlowOcc.<n>It is inspired by Gaussian Splatting and replaces traditional dense voxel grids with a sparse 3D Gaussian representation.
  arXiv  Detail & Related papers  (2025-02-24T16:16:01Z)
• GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction [55.60972844777044]
  3D semantic occupancy prediction is an important task for robust vision-centric autonomous driving.<n>Most existing methods leverage dense grid-based scene representations, overlooking the spatial sparsity of the driving scenes.<n>We propose a probabilistic Gaussian superposition model which interprets each Gaussian as a probability distribution of its neighborhood being occupied.
  arXiv  Detail & Related papers  (2024-12-05T17:59:58Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images [102.7646120414055]
  We introduce MVSplat, an efficient model that, given sparse multi-view images as input, predicts clean feed-forward 3D Gaussians. On the large-scale RealEstate10K and ACID benchmarks, MVSplat achieves state-of-the-art performance with the fastest feed-forward inference speed (22fps)
  arXiv  Detail & Related papers  (2024-03-21T17:59:58Z)
• Energy networks for state estimation with random sensors using sparse labels [0.0]
  We propose a technique with an implicit optimization layer and a physics-based loss function that can learn from sparse labels. Based on this technique we present two models for discrete and continuous prediction in space.
  arXiv  Detail & Related papers  (2022-03-12T15:15:38Z)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)
• Gravitational-wave parameter estimation with autoregressive neural network flows [0.0]
  We introduce the use of autoregressive normalizing flows for rapid likelihood-free inference of binary black hole system parameters from gravitational-wave data with deep neural networks. A normalizing flow is an invertible mapping on a sample space that can be used to induce a transformation from a simple probability distribution to a more complex one. We build a more powerful latent variable model by incorporating autoregressive flows within the variational autoencoder framework.
  arXiv  Detail & Related papers  (2020-02-18T15:44:04Z)

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.