将SDF学习嵌入3D高斯，实现更精确完整的表面重建。
Accurate and Complete Surface Reconstruction from 3D Gaussians via Direct SDF Learning
- 直接在3D高斯管线中引入可学习的有符号距离场（SDF）
- 在DTU、Mip-NeRF 360等基准上提升重建精度与完整性
- 适合关注几何重建质量的3D视觉研究者
3D高斯泼溅（3DGS）近年来成为生成逼真视角的有力范式，通过空间分布的高斯基元表示场景。尽管渲染效果出色，但因表示无结构且缺乏显式几何监督，实现精确完整的表面重建仍具挑战。本文提出DiGS框架，将有符号距离场（SDF）学习直接嵌入3DGS流程，从而施加强而可解释的表面先验。通过为每个高斯分配可学习的SDF值，DiGS显式对齐基元与底层几何，并提升跨视角一致性。为进一步确保密集连贯覆盖，设计了基于几何引导的网格生长策略，在多尺度层次下自适应分布高斯于几何一致区域。在标准基准（包括DTU、Mip-NeRF 360和Tanks& Temples）上的大量实验表明，DiGS在保持高渲染保真度的同时，持续提升重建准确性和完整性。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has recently emerged as a powerful paradigm for photorealistic view synthesis, representing scenes with spatially distributed Gaussian primitives. While highly effective for rendering, achieving accurate and complete surface reconstruction remains challenging due to the unstructured nature of the representation and the absence of explicit geometric supervision. In this work, we propose DiGS, a unified framework that embeds Signed Distance Field (SDF) learning directly into the 3DGS pipeline, thereby enforcing strong and interpretable surface priors. By associating each Gaussian with a learnable SDF value, DiGS explicitly aligns primitives with underlying geometry and improves cross-view consistency. To further ensure dense and coherent coverage, we design a geometry-guided grid growth strategy that adaptively distributes Gaussians along geometry-consistent regions under a multi-scale hierarchy. Extensive experiments on standard benchmarks, including DTU, Mip-NeRF 360, and Tanks& Temples, demonstrate that DiGS consistently improves reconstruction accuracy and completeness while retaining high rendering fidelity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。