Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequences

• URL: http://arxiv.org/abs/2602.22212v1
• Date: Wed, 25 Feb 2026 18:59:53 GMT
• Title: Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequences
• Authors: Julian Kaltheuner, Hannah Dröge, Markus Plack, Patrick Stotko, Reinhard Klein,
• Abstract summary: We present Neu-PiG, a fast deformation optimization method based on a novel preconditioned latent-grid encoding.<n>Our method encodes entire deformations across all time steps at various spatial scales into a multi-resolution latent grid.<n>To achieve high-fidelity, drift-free surface reconstructions in seconds, we employ Sobolev preconditioning during gradient-based training of the latent space.
• Score: 6.316764936463191
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Temporally consistent surface reconstruction of dynamic 3D objects from unstructured point cloud data remains challenging, especially for very long sequences. Existing methods either optimize deformations incrementally, risking drift and requiring long runtimes, or rely on complex learned models that demand category-specific training. We present Neu-PiG, a fast deformation optimization method based on a novel preconditioned latent-grid encoding that distributes spatial features parameterized on the position and normal direction of a keyframe surface. Our method encodes entire deformations across all time steps at various spatial scales into a multi-resolution latent grid, parameterized by the position and normal direction of a reference surface from a single keyframe. This latent representation is then augmented for time modulation and decoded into per-frame 6-DoF deformations via a lightweight multilayer perceptron (MLP). To achieve high-fidelity, drift-free surface reconstructions in seconds, we employ Sobolev preconditioning during gradient-based training of the latent space, completely avoiding the need for any explicit correspondences or further priors. Experiments across diverse human and animal datasets demonstrate that Neu-PiG outperforms state-the-art approaches, offering both superior accuracy and scalability to long sequences while running at least 60x faster than existing training-free methods and achieving inference speeds on the same order as heavy pretrained models.

Related papers

• EvolvingGS: High-Fidelity Streamable Volumetric Video via Evolving 3D Gaussian Representation [14.402479944396665]
  We introduce EvolvingGS, a two-stage strategy that first deforms the Gaussian model to align with the target frame, and then refines it with minimal point addition/subtraction.<n> Owing to the flexibility of the incrementally evolving representation, our method outperforms existing approaches in terms of both per-frame and temporal quality metrics.<n>Our method significantly advances the state-of-the-art in dynamic scene reconstruction, particularly for extended sequences with complex human performances.
  arXiv  Detail & Related papers  (2025-03-07T06:01:07Z)
• 4Deform: Neural Surface Deformation for Robust Shape Interpolation [47.47045870313048]
  We develop a new approach to generate realistic intermediate shapes between non-rigidly deformed shapes in unstructured data.<n>Our method learns a continuous velocity field in Euclidean space and does not require intermediate-shape supervision during training.<n>For the first time, our method enables new applications like 4D Kinect sequence upsampling and real-world high-resolution mesh deformation.
  arXiv  Detail & Related papers  (2025-02-27T15:47:49Z)
• Adaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic Reconstruction [3.9363268745580426]
  AT-GS is a novel method for reconstructing high-quality dynamic surfaces from multi-view videos through per-frame incremental optimization. We reduce temporal jittering in dynamic surfaces by ensuring consistency in curvature maps across consecutive frames. Our method achieves superior accuracy and temporal coherence in dynamic surface reconstruction, delivering high-fidelity space-time novel view synthesis.
  arXiv  Detail & Related papers  (2024-11-10T21:30:16Z)
• TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic Scene [25.164085646259856]
  This paper introduces a template-free 3D semantic NeRF for dynamic scenes captured from sparse or singleview RGB videos.<n>By disentangling the motions of interacting entities and optimizing per-entity skinning weights, our method efficiently generates accurate, semantically separable geometries.
  arXiv  Detail & Related papers  (2024-09-26T01:34:42Z)
• Graph and Skipped Transformer: Exploiting Spatial and Temporal Modeling Capacities for Efficient 3D Human Pose Estimation [36.93661496405653]
  We take a global approach to exploit Transformer-temporal information with a concise Graph and Skipped Transformer architecture. Specifically, in 3D pose stage, coarse-grained body parts are deployed to construct a fully data-driven adaptive model. Experiments are conducted on Human3.6M, MPI-INF-3DHP and Human-Eva benchmarks.
  arXiv  Detail & Related papers  (2024-07-03T10:42:09Z)
• Stable Surface Regularization for Fast Few-Shot NeRF [76.00444039563581]
  We develop a stable surface regularization technique called Annealing Signed Distance Function (ASDF) We observe that the Eikonal loss requires dense training signal to shape different level-sets of SDF, leading to low-fidelity results under few-shot training. The proposed approach is up to 45 times faster than existing few-shot novel view synthesis methods.
  arXiv  Detail & Related papers  (2024-03-29T05:39:47Z)
• SceNeRFlow: Time-Consistent Reconstruction of General Dynamic Scenes [75.9110646062442]
  We propose SceNeRFlow to reconstruct a general, non-rigid scene in a time-consistent manner. Our method takes multi-view RGB videos and background images from static cameras with known camera parameters as input. We show experimentally that, unlike prior work that only handles small motion, our method enables the reconstruction of studio-scale motions.
  arXiv  Detail & Related papers  (2023-08-16T09:50:35Z)
• Fast Monocular Scene Reconstruction with Global-Sparse Local-Dense Grids [84.90863397388776]
  We propose to directly use signed distance function (SDF) in sparse voxel block grids for fast and accurate scene reconstruction without distances. Our globally sparse and locally dense data structure exploits surfaces' spatial sparsity, enables cache-friendly queries, and allows direct extensions to multi-modal data. Experiments show that our approach is 10x faster in training and 100x faster in rendering while achieving comparable accuracy to state-of-the-art neural implicit methods.
  arXiv  Detail & Related papers  (2023-05-22T16:50:19Z)
• NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction [95.37644907940857]
  We propose a fast neural surface reconstruction approach, called NeuS2. NeuS2 achieves two orders of magnitude improvement in terms of acceleration without compromising reconstruction quality. We extend our method for fast training of dynamic scenes, with a proposed incremental training strategy and a novel global transformation prediction component.
  arXiv  Detail & Related papers  (2022-12-10T07:19:43Z)
• Neural Deformable Voxel Grid for Fast Optimization of Dynamic View Synthesis [63.25919018001152]
  We propose a fast deformable radiance field method to handle dynamic scenes. Our method achieves comparable performance to D-NeRF using only 20 minutes for training.
  arXiv  Detail & Related papers  (2022-06-15T17:49:08Z)
• Progressive Encoding for Neural Optimization [92.55503085245304]
  We show the competence of the PPE layer for mesh transfer and its advantages compared to contemporary surface mapping techniques. Most importantly, our technique is a parameterization-free method, and thus applicable to a variety of target shape representations.
  arXiv  Detail & Related papers  (2021-04-19T08:22:55Z)

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.