PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction
This work addresses the problem of efficient and high-quality 3D reconstruction for applications like large-scale scene modeling and embodied AI, representing an incremental advance by combining existing elements in a novel way.
The paper tackles the challenge of streaming 3D reconstruction from monocular images by introducing PLANING, a framework that loosely couples geometric primitives with neural Gaussians to achieve both high-quality rendering and accurate geometry, resulting in an 18.52% improvement in mesh Chamfer-L2, 1.31 dB PSNR gain, and reconstruction speeds over 5x faster than prior methods.
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/ .