用松耦合的三角形-高斯表示，实现快速高质量单目3D重建。
PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction
- 用显式几何体与神经高斯松耦合，分离建模几何与外观。
- 比PGSR提升18.52%稠密网格精度，比ARTDECO提升1.31dB PSNR。
- 重建ScanNetV2仅需<100秒，速度超2D高斯泼溅5倍，适合智能体仿真。
单目图像序列的流式重建仍具挑战，现有方法通常在渲染质量与几何准确性之间权衡，难以兼顾。本文提出PLANING，一种基于显式几何体与神经高斯松耦合的混合表示框架，支持几何与外观的解耦建模。该解耦设计使几何与外观更新可独立进行，实现在线初始化与优化，显著降低结构冗余，保障稳定流式重建。在密集网格上，其Chamfer-L2指标相比PGSR提升18.52%，在PSNR上超越ARTDECO 1.31 dB；可在100秒内完成ScanNetV2场景重建，速度超过2D高斯泼溅5倍，同时媲美离线全场景优化效果。该方法兼具结构清晰性与计算高效性，适用于大规模场景建模与具身智能仿真等下游应用。
原文摘要 · Abstract (English)
Streaming reconstruction from monocular image sequences remains challenging, as existing methods typically favor either high-quality rendering or accurate geometry, but rarely both. We present PLANING, an efficient on-the-fly reconstruction framework built on a hybrid representation that loosely couples explicit geometric primitives with neural Gaussians, enabling geometry and appearance to be modeled in a decoupled manner. This decoupling supports an online initialization and optimization strategy that separates geometry and appearance updates, yielding stable streaming reconstruction with substantially reduced structural redundancy. PLANING improves dense mesh Chamfer-L2 by 18.52% over PGSR, surpasses ARTDECO by 1.31 dB PSNR, and reconstructs ScanNetV2 scenes in under 100 seconds, over 5x faster than 2D Gaussian Splatting, while matching the quality of offline per-scene optimization. Beyond reconstruction quality, the structural clarity and computational efficiency of PLANING make it well suited for a broad range of downstream applications, such as enabling large-scale scene modeling and simulation-ready environments for embodied AI. Project page: https://city-super.github.io/PLANING/ .
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。