MonoPlane: Exploiting Monocular Geometric Cues for Generalizable 3D Plane Reconstruction

TL;DR

MonoPlane introduces a monocular geometric cue-based framework for generalizable 3D plane detection and reconstruction, combining neural network-derived depth and normals with RANSAC and multi-plane optimization to achieve state-of-the-art results in diverse settings.

Contribution

The paper proposes a novel monocular geometric cue-based pipeline that generalizes well across datasets for 3D plane reconstruction, surpassing prior methods in zero-shot scenarios.

Findings

Achieves state-of-the-art zero-shot plane reconstruction performance.

Demonstrates robustness and scalability in diverse real-world datasets.

Extends single-view to sparse-view 3D plane reconstruction.

Abstract

This paper presents a generalizable 3D plane detection and reconstruction framework named MonoPlane. Unlike previous robust estimator-based works (which require multiple images or RGB-D input) and learning-based works (which suffer from domain shift), MonoPlane combines the best of two worlds and establishes a plane reconstruction pipeline based on monocular geometric cues, resulting in accurate, robust and scalable 3D plane detection and reconstruction in the wild. Specifically, we first leverage large-scale pre-trained neural networks to obtain the depth and surface normals from a single image. These monocular geometric cues are then incorporated into a proximity-guided RANSAC framework to sequentially fit each plane instance. We exploit effective 3D point proximity and model such proximity via a graph within RANSAC to guide the plane fitting from noisy monocular depths, followed by image-level multi-plane joint optimization to improve the consistency among all plane instances. We further design a simple but effective pipeline to extend this single-view solution to sparse-view 3D plane reconstruction. Extensive experiments on a list of datasets demonstrate our superior zero-shot generalizability over baselines, achieving state-of-the-art plane reconstruction performance in a transferring setting. Our code is available at https://github.com/thuzhaowang/MonoPlane .