Skip to content
Preprint

TopoSurfel: Closing the Loop between Gaussian Surfels and Meshes for Surface Reconstruction

Aug 2026 · 0 citations · 48 references
Computer Science

TL;DR

This work proposes TopoSurfel, a novel framework that closes the loop between Gaussian surfels and continuous meshes, and introduces a mesh-guided surfel evolution strategy, including normal alignment and geometry-aware density control, to effectively suppress floaters and fill surface holes.

Abstract

3D Gaussian Splatting has achieved remarkable success in novel view synthesis. However, extracting high-fidelity surfaces directly from 3DGS remains challenging due to its discrete and unstructured nature. Existing 3DGS-based reconstruction methods typically rely on multi-view geometric consistency or local constraints. Without an explicit structured geometric prior during optimization, these methods often struggle to resolve structural ambiguities, leading to artifacts and floaters, particularly in textureless or occluded regions. To address this limitation, we propose TopoSurfel, a novel framework that closes the loop between Gaussian surfels and continuous meshes. Unlike recent methods that incorporate mesh extraction into the differentiable pipeline by introducing auxiliary neural networks or extra per-Gaussian parameters, we dynamically extract a continuous proxy mesh via a non-trainable differentiable iso-surfacing process. Leveraging this differentiable connection, we introduce a mesh-guided surfel evolution strategy, including normal alignment and geometry-aware density control, to effectively suppress floaters and fill surface holes. Furthermore, to address the initialization challenges in large-scale environments, we propose a spatially aware hybrid re-initialization strategy that ensures robust reconstruction across complex scenes. Extensive experiments demonstrate that TopoSurfel achieves competitive geometric reconstruction accuracy while maintaining high-quality mesh-based novel view synthesis. The code for our method is available at https://github.com/Fan-Treasure/TopoSurfel.

View source

Similar papers

Preprint Sep 2026

ToCo-Mesh: Topology-Consistent Dynamic Mesh Reconstruction via Adaptive Tessellation and Surface-Aligned 2DGS

Reconstructing dynamic meshes with consistent topology from multi-view temporal images remains a challenge. Existing approaches typically face a dilemma between fine-scale shape recovery and topological stability. Frame-by-frame extraction methods capture fine details but break vertex correspondence, leading to flicker...

Chuan-Jin Fan, Wen-Jie Chang, Ai-Bing Li et al. · 0 citations
Preprint Aug 2026

Elastic Triangle Splatting

While neural rendering methods such as 3D Gaussian Splatting achieve remarkable visual fidelity, traditional polygonal meshes remain the backbone of established graphics pipelines. Triangle splatting bridges this gap by optimizing triangle primitives as differentiable splats, producing representations that are closer t...

Tian Shi, Shenhan Qian, Daniel Cremers · 0 citations
Preprint Sep 2026

AnyGS2Mesh: Feed-Forward Mesh Reconstruction from 3D Gaussian Splatting with Arbitrary-Resolution Views

AnyGS2Mesh is presented, the first feed-forward framework for directly reconstructing 3D meshes from 3D Gaussian Splatting representations with support for arbitrary input image resolutions, and demonstrates the potential of combining Gaussian representations and feed-forward Transformer architectures for scalable 3D g...

Yuxuan Song, Fan Gao, Yi-Bo Zhao et al. · 0 citations
Preprint Oct 2026

MEGA: Object-Level Mesh Extraction from 3D Gaussian Splatting via Spatial Visual Distillation

Mesh extraction from 3D Gaussian Splatting (3DGS) aims to endow 3D Gaussians with accurate geometric structures, enabling explicit and precise 3D occupancy. However, existing methods primarily focus on scene-level mesh extraction, making them unable to represent object-level occupancy and often resulting in non-waterti...

Li-Wei Liao, Ying-Kui Zhang, Qian-Qian Tong et al. · 0 citations
Preprint Aug 2026

RADmesh: Remesh-Aware Mesh Deformation

A vertex-based deformation optimization quantity capable of large deformations and robustness to such noise is proposed, periodically remesh using an isotropic remesher that interpolates and carries forward the deformation optimization state.

Nam Anh Dinh, Itai Lang, Oded Stein et al. · 0 citations
Preprint Sep 2026

ADELE - Adaptive Delaunay Grids for High-Fidelity Mesh-Native Reconstruction

This paper introduces an adaptive mesh-based optimization framework and a practical mesh rendering technique that significantly outperforms existing mesh optimization approaches across a variety of object-centric benchmarks while being competitive with state-of-the-art NeRF/3DGS methods.

Johannes Weidenfeller, Shaofei Wang, P. Fürnstahl et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.