发表机构
ETH Zurich; Beijing Institute for General Artificial Intelligence; University of Zurich; Balgrist University Hospital（苏黎世联邦理工学院; 北京通用人工智能研究院; 苏黎世大学; 巴尔格里斯特大学医院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出ADELE自适应网格优化框架，结合Delaunay四面体网格与哈希网格，通过点剪枝插入和深度偏移渲染，实现高保真网格原生重建，性能优于现有网格方法并媲美NeRF/3DGS。
AI 中文摘要
网格仍然是几何推理和集成到图形管线中最实用的表示形式，然而现有的重建方法难以生成高质量的网格。大多数最先进的方法最初学习中间表示（NeRF/3DGS），并将网格提取视为后处理步骤，这常常导致表面过度平滑或产生具有过多三角形的低质量网格。虽然网格原生优化方法缓解了其中一些问题，但受限于固定分辨率离散化和不稳定的优化行为。在本文中，我们引入了一种自适应网格优化框架和一种实用的网格渲染技术来解决这些挑战。我们的表示结合了可优化的Delaunay三角化四面体网格与多分辨率哈希网格。前者通过点剪枝和插入进行细化，而后者为SDF/外观值预测提供潜在特征。我们使用体渲染来引导粗略几何，同时利用基于网格的渲染来恢复细粒度细节。此外，我们提出了一种可微分的、基于光栅化的深度偏移渲染公式，减少了几何伪影并提高了重建质量。我们的方法在各种以物体为中心的基准测试中显著优于现有的网格优化方法，同时与最先进的NeRF/3DGS方法相比具有竞争力。
英文摘要
Meshes remain the most practical representation for geometry reasoning and integration into graphics pipelines, yet existing reconstruction methods struggle to produce high-quality meshes. Most state-of-the-art approaches initially learn an intermediate representation (NeRF/3DGS) and treat mesh extraction as a post-processing step, which often leads to oversmoothed surfaces or poor quality meshes with excessive triangle counts.Existing mesh-native optimization methods alleviate some of these issues but suffer from fixed-resolution discretizations and unstable optimization behavior. In this paper, we introduce an adaptive mesh-based optimization framework and a practical mesh rendering technique to address these challenges. Our representation combines an optimizable Delaunay-triangulated tetrahedral grid with a multi-resolution hash grid. The former is refined through point pruning and insertion, while the latter provides latent features for SDF/appearance value predictions. We use volumetric rendering to bootstrap a coarse geometry while leveraging mesh-based rendering for recovering fine-grained details. Additionally, we propose a differentiable, rasterization-based depth-offset rendering formulation, reducing geometric artifacts and improving reconstruction quality. Our method significantly outperforms existing mesh optimization approaches across a variety of object-centric benchmarks while being competitive with state-of-the-art NeRF/3DGS methods.
CommentsAccepted to SIGGRAPH Asia 2026 Conference Papers | Project page: https://johannes-weidenfeller.github.io/adele | Code: https://github.com/johannes-weidenfeller/adele
