Year: 2025
Type: conference-paper
Abstract: We present UniPlane, a novel approach that unifies plane detection and reconstruction from posed monocular videos. Unlike existing methods that detect planes from local observations and associate them across the video for the final reconstruction, UniPlane unifies both the detection and the reconstruction tasks in a single network, which allows us to directly optimize final reconstruction quality and fully leverage temporal information. Specifically, we build a Transformers-based deep neural network that jointly constructs a 3D feature volume for the environment and estimates a set of per-plane embeddings as queries. UniPlane directly reconstructs the 3D planes by taking dot products between voxel embeddings and the plane embeddings followed by binary thresholding. Extensive experiments on real-world datasets demonstrate that UniPlane outperforms state-of-the-art methods in both plane detection and reconstruction tasks, achieving +4.6 in F-score in geometry as well as consistent improvements in other geometry and segmentation metrics.
Authors: Yuzhong Huang, Fred Morstatter
Institution: University of Southern California
Language: English
Topic: Advanced Vision and Imaging
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4408345719