ARTDECO：基于结构化场景表示的高效高保真实时三维重建

ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation

October 9, 2025

作者: Guanghao Li, Kerui Ren, Linning Xu, Zhewen Zheng, Changjian Jiang, Xin Gao, Bo Dai, Jian Pu, Mulin Yu, Jiangmiao Pang

cs.AI

摘要

基于单目图像序列的实时三维重建是计算机视觉领域长期面临的挑战，对于真实到虚拟（real-to-sim）、增强现实/虚拟现实（AR/VR）以及机器人技术等应用至关重要。现有方法面临一个主要权衡：针对特定场景的优化虽能获得高保真度，但计算成本高昂；而前馈式基础模型虽能实现实时推理，却在精度和鲁棒性上表现欠佳。本文提出ARTDECO，一个统一框架，它结合了前馈模型的高效性与基于SLAM（同步定位与地图构建）管道的可靠性。ARTDECO利用三维基础模型进行姿态估计与点云预测，并配备一个高斯解码器，将多尺度特征转化为结构化的三维高斯分布。为了在保持高保真度的同时实现大规模场景下的高效处理，我们设计了一种层次化的高斯表示方法，结合细节层次（LoD）感知的渲染策略，既提升了渲染质量又减少了冗余。在八个多样化的室内外基准测试上的实验表明，ARTDECO在交互性能上可与SLAM媲美，在鲁棒性上接近前馈系统，重建质量则逼近针对特定场景的优化结果，为实时数字化真实世界环境提供了一条实用路径，兼具精确几何与高视觉保真度。更多演示请访问我们的项目页面：https://city-super.github.io/artdeco/。

English

On-the-fly 3D reconstruction from monocular image sequences is a long-standing challenge in computer vision, critical for applications such as real-to-sim, AR/VR, and robotics. Existing methods face a major tradeoff: per-scene optimization yields high fidelity but is computationally expensive, whereas feed-forward foundation models enable real-time inference but struggle with accuracy and robustness. In this work, we propose ARTDECO, a unified framework that combines the efficiency of feed-forward models with the reliability of SLAM-based pipelines. ARTDECO uses 3D foundation models for pose estimation and point prediction, coupled with a Gaussian decoder that transforms multi-scale features into structured 3D Gaussians. To sustain both fidelity and efficiency at scale, we design a hierarchical Gaussian representation with a LoD-aware rendering strategy, which improves rendering fidelity while reducing redundancy. Experiments on eight diverse indoor and outdoor benchmarks show that ARTDECO delivers interactive performance comparable to SLAM, robustness similar to feed-forward systems, and reconstruction quality close to per-scene optimization, providing a practical path toward on-the-fly digitization of real-world environments with both accurate geometry and high visual fidelity. Explore more demos on our project page: https://city-super.github.io/artdeco/.