NVC-GS: Monocular Dynamic Scene Reconstruction via Normal-Regularized and Multi-View-Consistent 3D Gaussian Splatting

Huiwen Xue, Kaixing Zhao, Tingcheng Li, Tao Xu, Zuheng Ming

Keywords: Novel View Synthesis, 3D Gaussian Splatting, Dynamic Scene Reconstruction

TL;DR: Normal-Regularized and Multi-View-Consistent Gaussian Splatting (NVC-GS) enables real-time, high-quality dynamic scene reconstruction by combining geometry-aware normal regularization and diffusion-based multi-view consistency.

Abstract: High-quality, real-time dynamic scene reconstruction and rendering are essential for immersive applications. While techniques like 3D Gaussian Splatting (3DGS) succeed in static scenes, dynamic monocular scenarios still suffer from deformation, surface noise, and inconsistent view-dependent effects due to insufficient geometric constraints and inadequate multi-view consistency enforcement for monocular input. To address these challenges, we present Normal-Regularized and Multi-View-Consistent Gaussian Splatting (NVC-GS), a novel approach combining geometry-aware normal regularization with diffusion-based multi-view consistency. Our method explicitly preserves geometric consistency in dynamic objects through tailored normal constraints, while leveraging diffusion-driven latent space regularization to ensure cross-view rendering consistency, particularly for complex materials such as reflective surfaces. Experimental results demonstrate that our approach effectively improves geometric accuracy and visual quality in dynamic scenes while maintaining real-time capabilities, outperforming existing methods in terms of deformation handling, surface noise reduction, and rendering of reflective materials.

Submission Number: 266