SirenPose: Dynamic Scene Reconstruction via Geometric Supervision

• URL: http://arxiv.org/abs/2512.20531v1
• Date: Tue, 23 Dec 2025 17:23:21 GMT
• Title: SirenPose: Dynamic Scene Reconstruction via Geometric Supervision
• Authors: Kaitong Cai, Jensen Zhang, Jing Yang, Keze Wang,
• Abstract summary: We introduce SirenPose, a geometry-aware loss formulation that integrates the periodic activation of properties sinusoidal representation networks with keypoint-based geometric supervision.<n>In pose estimation, SirenPose outperforms Monst3R with lower absolute trajectory error as well as reduced translational and rotational relative pose error.
• Score: 12.966077380225856
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce SirenPose, a geometry-aware loss formulation that integrates the periodic activation properties of sinusoidal representation networks with keypoint-based geometric supervision, enabling accurate and temporally consistent reconstruction of dynamic 3D scenes from monocular videos. Existing approaches often struggle with motion fidelity and spatiotemporal coherence in challenging settings involving fast motion, multi-object interaction, occlusion, and rapid scene changes. SirenPose incorporates physics inspired constraints to enforce coherent keypoint predictions across both spatial and temporal dimensions, while leveraging high frequency signal modeling to capture fine grained geometric details. We further expand the UniKPT dataset to 600,000 annotated instances and integrate graph neural networks to model keypoint relationships and structural correlations. Extensive experiments on benchmarks including Sintel, Bonn, and DAVIS demonstrate that SirenPose consistently outperforms state-of-the-art methods. On DAVIS, SirenPose achieves a 17.8 percent reduction in FVD, a 28.7 percent reduction in FID, and a 6.0 percent improvement in LPIPS compared to MoSCA. It also improves temporal consistency, geometric accuracy, user score, and motion smoothness. In pose estimation, SirenPose outperforms Monst3R with lower absolute trajectory error as well as reduced translational and rotational relative pose error, highlighting its effectiveness in handling rapid motion, complex dynamics, and physically plausible reconstruction.

Related papers

• Stereo-Inertial Poser: Towards Metric-Accurate Shape-Aware Motion Capture Using Sparse IMUs and a Single Stereo Camera [54.967647497048205]
  We present Stereo-Inertial Poser, a real-time motion capture system that estimates metric-accurate and shape-aware 3D human motion.<n>We replace the monocular RGB with stereo vision, enabling direct 3D keypoint extraction and body shape parameter estimation.<n>Our method produces drift-free global translation under a long recording time and reduces foot-skating effects.
  arXiv  Detail & Related papers  (2026-03-02T17:46:38Z)
• Learning Dynamic Scene Reconstruction with Sinusoidal Geometric Priors [8.153339288887922]
  We propose SirenPose, a novel loss function that combines the periodic activation of sinusoidal representation networks with geometric priors derived from keypoint structures to improve the accuracy of 3D scene reconstruction.
  arXiv  Detail & Related papers  (2025-12-25T20:51:19Z)
• Towards Arbitrary Motion Completing via Hierarchical Continuous Representation [64.6525112550758]
  We propose a novel parametric activation-induced hierarchical implicit representation framework, called NAME, based on Implicit Representations (INRs)<n>Our method introduces a hierarchical temporal encoding mechanism that extracts features from motion sequences at multiple temporal scales, enabling effective capture of intricate temporal patterns.
  arXiv  Detail & Related papers  (2025-12-24T14:07:04Z)
• KineST: A Kinematics-guided Spatiotemporal State Space Model for Human Motion Tracking from Sparse Signals [11.14439818111551]
  Full-body motion tracking plays an essential role in AR/VR applications, bridging physical and virtual interactions.<n>It is challenging to reconstruct realistic and diverse full-body poses based on sparse signals obtained by head-mounted displays.<n>Existing methods for pose reconstruction often incur high computational costs or rely on separately spatial modeling and temporal dependencies.<n>We propose KineST, a novel kinematics-guided state space model, which effectively extracts geometric dependencies while integrating local and global pose perception.
  arXiv  Detail & Related papers  (2025-12-18T17:25:47Z)
• HAD: Hierarchical Asymmetric Distillation to Bridge Spatio-Temporal Gaps in Event-Based Object Tracking [80.07224739976911]
  Event cameras offer exceptional temporal resolution and a range (modal)<n> RGB cameras excel at capturing rich texture with high resolution, whereas event cameras offer exceptional temporal resolution and a range (modal)
  arXiv  Detail & Related papers  (2025-10-22T13:15:13Z)
• SplitGaussian: Reconstructing Dynamic Scenes via Visual Geometry Decomposition [14.381223353489062]
  We propose textbfSplitGaussian, a novel framework that explicitly decomposes scene representations into static and dynamic components.<n>SplitGaussian outperforms prior state-of-the-art methods in rendering quality, geometric stability, and motion separation.
  arXiv  Detail & Related papers  (2025-08-06T09:00:13Z)
• 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)
• EMoTive: Event-guided Trajectory Modeling for 3D Motion Estimation [59.33052312107478]
  Event cameras offer possibilities for 3D motion estimation through continuous adaptive pixel-level responses to scene changes.<n>This paper presents EMove, a novel event-based framework that models-uniform trajectories via event-guided parametric curves.<n>For motion representation, we introduce a density-aware adaptation mechanism to fuse spatial and temporal features under event guidance.<n>The final 3D motion estimation is achieved through multi-temporal sampling of parametric trajectories, flows and depth motion fields.
  arXiv  Detail & Related papers  (2025-03-14T13:15:54Z)
• Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry [7.517597541959445]
  We introduce S-Temporal Visual Odometry (STVO), a novel deep network architecture to enhance accuracy and consistency of multi-frame flow matching.<n>Our STVO achieves state-the-art performance on ETH3D benchmark and 38.9% on KITTI Odometry benchmark over the previous best methods.
  arXiv  Detail & Related papers  (2024-12-22T08:47:13Z)
• 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)
• 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)
• InstantSplat: Sparse-view Gaussian Splatting in Seconds [91.77050739918037]
  We introduce InstantSplat, a novel approach for addressing sparse-view 3D scene reconstruction at lightning-fast speed.<n>InstantSplat employs a self-supervised framework that optimize 3D scene representation and camera poses.<n>It achieves an acceleration of over 30x in reconstruction and improves visual quality (SSIM) from 0.3755 to 0.7624 compared to traditional SfM with 3D-GS.
  arXiv  Detail & Related papers  (2024-03-29T17:29:58Z)

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.