PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction

2026-01-29

AI Summary

Streaming 3D reconstruction from monocular image sequences struggles to simultaneously achieve high-quality rendering and geometric accuracy. This work proposes a loosely coupled representation framework that combines explicit triangular primitives with neural Gaussians, decoupling geometry and appearance for the first time to enable independent online optimization of both components. By disentangling these representations, the method substantially reduces structural redundancy, leading to improved reconstruction efficiency and fidelity. Evaluated on ScanNetV2, the approach achieves a fivefold speedup over 2D Gaussian Splatting—completing reconstruction in under 100 seconds—while outperforming PGSR by 18.52% in Chamfer-L2 distance and surpassing ARTDECO by 1.31 dB in PSNR, attaining reconstruction quality comparable to offline optimization methods.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Representation Learning

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

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/ .

Problem

• streaming 3D reconstruction
• monocular image sequences
• geometry-accuracy
• rendering quality
• real-time reconstruction

Innovation

• Triangle-Gaussian representation
• Loosely coupled reconstruction
• Streaming 3D reconstruction
• Decoupled geometry-appearance modeling
• Neural Gaussians