Scholarlink

<p>3D Gaussian Splatting (3D-GS) enables real-time, photorealistic view synthesis, but its radiance is tied to the captured lighting and its point-like representation is incompatible with standard digital content creation tools, game engines, and simulation platforms. Existing surface extraction methods typically defer converting splats to polygons until after photometric optimization, resulting in blurred edges, inflated planar regions, and loss of fine geometric details due to the continuous nature of Gaussian densities. This paper proposes a surface-oriented, differentiable optimization framework to overcome these issues. Our approach introduces a triangle-soup optimization pipeline that transforms a pre-trained 3D-GS model into a high-quality manifold mesh, preserving sharp features and fine geometry. Specifically, it starts with sharpening the opacity of input splats to better align with underlying surfaces. Each visible splat is then replaced by a compact triangle pair, followed by an image-driven, geometry-aware optimization that refines the resulting triangle-soup. This yields a compact, feature-preserving, and size-adaptive triangle set that can be sealed into a watertight surface using standard wrapping software tools with minimal post-processing loss. Experiments on synthetic, indoor, and object-level reconstruction benchmarks show that our method improves mesh quality over representative GS-to-mesh baselines and achieves competitive geometric accuracy against recent GS-based surface reconstruction methods.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

SplatSurf: bridging Gaussian splatting and surface geometry via triangle-soup

  • 期刊论文

  • 发表日期：

    2026年7月11日

查看全文
  • Hezi Shi,
  • Jianmin Zheng

摘要

3D Gaussian Splatting (3D-GS) enables real-time, photorealistic view synthesis, but its radiance is tied to the captured lighting and its point-like representation is incompatible with standard digital content creation tools, game engines, and simulation platforms. Existing surface extraction methods typically defer converting splats to polygons until after photometric optimization, resulting in blurred edges, inflated planar regions, and loss of fine geometric details due to the continuous nature of Gaussian densities. This paper proposes a surface-oriented, differentiable optimization framework to overcome these issues. Our approach introduces a triangle-soup optimization pipeline that transforms a pre-trained 3D-GS model into a high-quality manifold mesh, preserving sharp features and fine geometry. Specifically, it starts with sharpening the opacity of input splats to better align with underlying surfaces. Each visible splat is then replaced by a compact triangle pair, followed by an image-driven, geometry-aware optimization that refines the resulting triangle-soup. This yields a compact, feature-preserving, and size-adaptive triangle set that can be sealed into a watertight surface using standard wrapping software tools with minimal post-processing loss. Experiments on synthetic, indoor, and object-level reconstruction benchmarks show that our method improves mesh quality over representative GS-to-mesh baselines and achieves competitive geometric accuracy against recent GS-based surface reconstruction methods.