DySurface: Consistent 4D Surface Reconstruction via Bridging Explicit Gaussians and Implicit Functions

2026-05-11

AI Summary

High-quality, temporally consistent geometric surface reconstruction in dynamic scenes is challenged by surface discontinuities and artifacts. This work proposes VoxGS-DSDF, a novel approach that, for the first time, leverages deformed explicit 3D Gaussians as geometric anchors to regularize implicit signed distance field (SDF) rendering. By aligning forward Gaussian deformation with backward SDF rendering, the method constructs a dynamic sparse voxel grid that guides the implicit field. This strategy effectively bridges the structural inconsistency between explicit and implicit representations, significantly enhancing geometric accuracy and detail fidelity. Consequently, VoxGS-DSDF achieves watertight, temporally coherent 4D surface reconstruction while maintaining excellent rendering quality.

Abstract

While novel view synthesis (NVS) for dynamic scenes has seen significant progress, reconstructing temporally consistent geometric surfaces remains a challenge. Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) offer powerful dynamic scene rendering capabilities; however, relying solely on photometric optimization often leads to geometric ambiguities. This results in discontinuous surfaces, severe artifacts, and broken surfaces over time. To address these limitations, we present DySurface, a novel framework that bridges the effectiveness of explicit Gaussians with the geometric fidelity of implicit Signed Distance Functions (SDFs) in dynamic scenes. Our approach tackles the structural discrepancy between the forward deformation of 3DGS ($canonical \rightarrow dynamic$) and the backward deformation required for volumetric SDF rendering ($dynamic \rightarrow canonical$). Specifically, we propose the VoxGS-DSDF branch that leverages deformed Gaussians to construct a dynamic sparse voxel grid, providing explicit geometric guidance to the implicit SDF field. This explicit anchoring effectively regularizes the volumetric rendering process, significantly improving surface reconstruction quality, with watertight boundaries and detailed representations. Quantitative and qualitative experiments demonstrate that DySurface significantly outperforms state-of-the-art baselines in geometric accuracy metrics while maintaining competitive rendering performance.

Problem

• dynamic scenes
• surface reconstruction
• temporal consistency
• geometric ambiguity
• 4D reconstruction

Innovation

• Dynamic Surface Reconstruction
• 3D Gaussian Splatting
• Signed Distance Function
• Temporal Consistency
• Explicit-Implicit Fusion