Pixel-wise Planarity for High-Precision Monocular Plane Segmentation

Researchers Alpay Ozkan and colleagues introduced a pixel-wise planarity prediction framework for monocular plane segmentation from a single RGB image, published as arXiv:2609.13246v1. The method adds a dedicated planarity head to a pretrained monocular geometric backbone that predicts depth and surface normals, then combines per-pixel depth, normals, and planarity confidence in a lightweight region-growing procedure during inference. The authors report improved geometric precision and segmentation quality over prior state-of-the-art approaches across multiple datasets, along with better computational efficiency, and released code and models at https://github.com/alpayozkan/PixelwisePlanarity.

arXiv:2609.13246v1 Announce Type: new Abstract: Plane segmentation from a single RGB image remains challenging due to imprecise region grouping and geometrically inconsistent supervision, often leading to over-segmentation and false planar detections. We propose instead a pixel-wise planarity prediction framework for robust monocular plane segmentation. Building on a pretrained monocular geometric backbone predicting depth and surface normals, we introduce a dedicated planarity head that estimates per-pixel planarity confidence. During inference, predicted depth, normals, and planarity are combined in a lightweight region-growing procedure that enforces geometric consistency when forming plane segments. We further analyze existing plane ground-truth annotations and demonstrate substantial geometric inconsistencies under strict distance thresholds. Across multiple datasets, our method achieves improved geometric precision and segmentation quality compared to prior state-of-the-art approaches, while improving computational efficiency. Our code and models are available at https://github.com/alpayozkan/PixelwisePlanarity.