cs.CVNov 17, 2026

OCLDA-GS: Object-Centric Local Deformation-Aware Gaussian Streaming

Authors: Ashim Dahal, Nikesh Subedi, Rabab Abdelfattah, Nick Rahimi

Organizations: University of Southern Mississippi, Hattiesburg, MS · University of Utah, Salt Lake City, UT

Abstract

Streaming 3D Gaussian Splatting (3DGS) allows for online reconstruction of dynamic scenes from multi-view videos for Free Viewpoint Video (FVV). Current time and storage efficient methods rely on selecting a subset of anchor Gaussians and neighborhood interpolation for fast streamable 3DGS. However, these methods can overlook object-specific motion and introduce inconsistencies near object boundaries. We propose OCLDA-GS, an object-centric streaming framework that dynamically reallocates object and motion-aware Gaussian anchors to allocate anchor Gaussian support for objects undergoing large motion while at the same time, restricting the gaussian neighborhood within object groups for more precise object boundaries. Furthermore, it estimates object-wise rigid transformations (e.g. a hand moving) and leverages these estimates to learn per-anchor local deformation correction for small deformations (e.g. wrinkles on a shirt). Then, we conduct experiments on three dynamic multi-view video datasets and demonstrate improvements over the previous baselines alongside improved quality between refinement timesteps. Under matched refinement budgets, our method improves PSNR over Instant Gaussian Stream (IGS) by 0.169 dB on N3DV, 0.202 dB on Meeting Room and +0.199 on Google Immersive, while reducing the mean PSNR drop between refinement timesteps by 9.2% and 13.8% in N3DV and Meeting Room, respectively.

Figures & tables

Explore similar work

CardsList
  1. DecoGS: Adaptive Static-Dynamic Decoupling of 3D Gaussians for Free-Viewpoint Video Streaming

    Sep 15, 2026Idil Sulo, Alexey Supikov, Ilke Demir +13D Gaussian SplattingStreaming 3D Reconstruction

  2. FreeStreamGS: Online Feed-forward 3D Gaussian Splatting from Unposed Streaming Inputs

    Jun 2, 2026Ruiyang Chen, Feiran Li, Chu Zhou +33D Gaussian SplattingStreaming 3D Reconstruction

  3. MoRGS: Efficient Per-Gaussian Motion Reasoning for Streamable Dynamic 3D Scenes

    Mar 26, 2026Wonjoon Lee, Sungmin Woo, Donghyeong Kim +3Dynamic Scene Reconstruction4D Reconstruction