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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Changjian, Ren, Kerui, Li, Xudong, Song, Kaiwen, Li, Guanghao, Xu, Linning, Lu, Tao, Dong, Junting, Zhang, Yu, Dai, Bo, Yu, Mulin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910048989478912
author Jiang, Changjian
Ren, Kerui
Li, Xudong
Song, Kaiwen
Li, Guanghao
Xu, Linning
Lu, Tao
Dong, Junting
Zhang, Yu
Dai, Bo
Yu, Mulin
author_facet Jiang, Changjian
Ren, Kerui
Li, Xudong
Song, Kaiwen
Li, Guanghao
Xu, Linning
Lu, Tao
Dong, Junting
Zhang, Yu
Dai, Bo
Yu, Mulin
contents 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/ .
format Preprint
id arxiv_https___arxiv_org_abs_2601_22046
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction
Jiang, Changjian
Ren, Kerui
Li, Xudong
Song, Kaiwen
Li, Guanghao
Xu, Linning
Lu, Tao
Dong, Junting
Zhang, Yu
Dai, Bo
Yu, Mulin
Computer Vision and Pattern Recognition
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/ .
title PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.22046