Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors

• URL: http://arxiv.org/abs/2604.09366v1
• Date: Fri, 10 Apr 2026 14:36:50 GMT
• Title: Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors
• Abstract summary: We present a framework designed to disentangle dynamic and static components by modeling uncertainty across different stages of the reconstruction process.<n>Our approach reduces Mean Accuracy error by 13.43% and improves segmentation F-measure by 10.49%.<n>Our framework maintains the efficiency of feed-forward inference and requires no task-specific fine-tuning or per-scene optimization.
• Score: 38.939519059502025
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences where motion causes significant geometric ambiguity. To address this, we present a framework designed to disentangle dynamic and static components by modeling uncertainty across different stages of the reconstruction process. Our approach introduces three synergistic mechanisms: (1) Entropy-Guided Subspace Projection, which leverages information-theoretic weighting to adaptively aggregate multi-head attention distributions, effectively isolating dynamic motion cues from semantic noise; (2) Local-Consistency Driven Geometry Purification, which enforces spatial continuity via radius-based neighborhood constraints to eliminate structural outliers; and (3) Uncertainty-Aware Cross-View Consistency, which formulates multi-view projection refinement as a heteroscedastic maximum likelihood estimation problem, utilizing depth confidence as a probabilistic weight. Experiments on dynamic benchmarks show that our approach outperforms current state-of-the-art methods, reducing Mean Accuracy error by 13.43\% and improving segmentation F-measure by 10.49\%. Our framework maintains the efficiency of feed-forward inference and requires no task-specific fine-tuning or per-scene optimization.

Related papers

• Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation [81.44955493339835]
  DeGO is a deformable Gaussian occupancy framework that unifies decoupled Gaussian deformation with factorized 4D foundation-model distillation.<n> Experiments on the Occ3D-NuScenes benchmark demonstrate that our method achieves state-of-the-art performance under weak supervision.
  arXiv  Detail & Related papers  (2026-05-27T15:09:55Z)
• 4DVGGT-D: 4D Visual Geometry Transformer with Improved Dynamic Depth Estimation [38.64669047442234]
  We propose a training-free progressive decoupling framework that disentangles dynamics from statics in a principled, coarse-to-fine manner.<n>Our approach shows competitive performance in robust 4D scene reconstruction without requiring fine-tuning.
  arXiv  Detail & Related papers  (2026-05-12T12:13:36Z)
• Mesh Based Simulations with Spatial and Temporal awareness [2.867517731896504]
  We propose a unified framework to bridge the gap between geometric deep learning and rigorous numerical analysis.<n>We introduce three key innovations: (1) Multi Node Prediction, a stencil-level objective that predicts field values for a node's full local topology, enforcing spatial derivative consistency; (2) Temporal Correction, replacing unstable explicit schemes with a predictor-corrector via temporal Cross-Attention; and (3) Geometric Inductive Biases, leveraging 3D Rotary Positional Embeddings (RoPE) to robustly capture rotational symmetries in unstructured meshes.
  arXiv  Detail & Related papers  (2026-05-02T17:09:31Z)
• NRGS: Neural Regularization for Robust 3D Semantic Gaussian Splatting [41.21645092733966]
  We propose a neural regularization method that refines the noisy 3D semantic field produced by lifting multi-view inconsistent 2D features.<n> Experiments show that our method enhances the accuracy of lifted semantics, providing an efficient and effective approach to robust 3D semantic Gaussian Splatting.
  arXiv  Detail & Related papers  (2026-04-24T10:57:05Z)
• DRoPS: Dynamic 3D Reconstruction of Pre-Scanned Objects [39.92394397834325]
  We present DRoPS, a novel approach that leverages a static pre-scan of the dynamic object as an explicit geometric and appearance prior.<n>Our method significantly outperforms the current state of the art in rendering quality and 3D tracking accuracy.
  arXiv  Detail & Related papers  (2026-03-25T19:41:50Z)
• GeoMotion: Rethinking Motion Segmentation via Latent 4D Geometry [61.24189040578178]
  We propose a fully learning-based approach that directly infers moving objects from latent feature representations via attention mechanisms.<n>Our key insight is to bypass explicit correspondence estimation and instead let the model learn to implicitly disentangle object and camera motion.<n>Our approach achieves state-of-the-art motion segmentation performance with high efficiency.
  arXiv  Detail & Related papers  (2026-02-25T11:36:33Z)
• From Tokens to Nodes: Semantic-Guided Motion Control for Dynamic 3D Gaussian Splatting [26.57713792657793]
  We propose a motion-adaptive framework that aligns control density with motion complexity.<n>We show significant improvements in reconstruction quality and efficiency over existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-10-03T05:33:58Z)
• Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts [80.32933059529135]
  Test-Time Adaptation (TTA) methods have emerged to adapt to target distributions during inference.<n>We propose Dual Uncertainty Optimization (DUO), the first TTA framework designed to jointly minimize both uncertainties for robust M3OD.<n>In parallel, we design a semantic-aware normal field constraint that preserves geometric coherence in regions with clear semantic cues.
  arXiv  Detail & Related papers  (2025-08-28T07:09:21Z)
• Delving into Dynamic Scene Cue-Consistency for Robust 3D Multi-Object Tracking [16.366398265001422]
  3D multi-object tracking is a critical and challenging task in the field of autonomous driving.<n>We introduce the Dynamic Scene Cue-Consistency Tracker (DSC-Track) to implement this principle.
  arXiv  Detail & Related papers  (2025-08-15T08:48:13Z)
• Tensor-Var: Efficient Four-Dimensional Variational Data Assimilation [30.63086465547801]
  Four-dimensional variational assimilation (4D-Var) faces high computational costs in complex nonlinear systems and depends on imperfect state-observation mappings.<n>Deep learning (DL) offers more expressive approximators, while integrating DL models into 4D-Var is challenging due to their nonlinearities and lack of theoretical guarantees in assimilation results.<n>We propose a novel framework that integrates kernel conditional mean embedding (CME) with 4D-Var to linearize nonlinear dynamics, achieving convex optimization in a learned feature space.
  arXiv  Detail & Related papers  (2025-01-23T01:43:31Z)
• 3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction [50.07071392673984]
  Existing methods learn 3D rotations parametrized in the spatial domain using angles or quaternions. We propose a frequency-domain approach that directly predicts Wigner-D coefficients for 3D rotation regression. Our method achieves state-of-the-art results on benchmarks such as ModelNet10-SO(3) and PASCAL3D+.
  arXiv  Detail & Related papers  (2024-11-01T12:50:38Z)
• MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion [118.74385965694694]
  We present Motion DUSt3R (MonST3R), a novel geometry-first approach that directly estimates per-timestep geometry from dynamic scenes.<n>By simply estimating a pointmap for each timestep, we can effectively adapt DUST3R's representation, previously only used for static scenes, to dynamic scenes.<n>We show that by posing the problem as a fine-tuning task, identifying several suitable datasets, and strategically training the model on this limited data, we can surprisingly enable the model to handle dynamics.
  arXiv  Detail & Related papers  (2024-10-04T18:00:07Z)

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.