Saved in:
Bibliographic Details
Main Authors: Bhattacharjee, Subhransu S., Campbell, Dylan, Shome, Rahul
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.16016
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910055284080640
author Bhattacharjee, Subhransu S.
Campbell, Dylan
Shome, Rahul
author_facet Bhattacharjee, Subhransu S.
Campbell, Dylan
Shome, Rahul
contents A single egocentric image typically captures only a small portion of the floor, yet a complete metric traversability map of the surroundings would better serve applications such as indoor navigation. We introduce FlatLands, a dataset and benchmark for single-view bird's-eye view (BEV) floor completion. The dataset contains 270,575 observations from 17,656 real metric indoor scenes drawn from six existing datasets, with aligned observation, visibility, validity, and ground-truth BEV maps, and the benchmark includes both in- and out-of-distribution evaluation protocols. We compare training-free approaches, deterministic models, ensembles, and stochastic generative models. Finally, we instantiate the task as an end-to-end monocular RGB-to-floormaps pipeline. FlatLands provides a rigorous testbed for uncertainty-aware indoor mapping and generative completion for embodied navigation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16016
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FlatLands: Generative Floormap Completion From a Single Egocentric View
Bhattacharjee, Subhransu S.
Campbell, Dylan
Shome, Rahul
Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
Image and Video Processing
A single egocentric image typically captures only a small portion of the floor, yet a complete metric traversability map of the surroundings would better serve applications such as indoor navigation. We introduce FlatLands, a dataset and benchmark for single-view bird's-eye view (BEV) floor completion. The dataset contains 270,575 observations from 17,656 real metric indoor scenes drawn from six existing datasets, with aligned observation, visibility, validity, and ground-truth BEV maps, and the benchmark includes both in- and out-of-distribution evaluation protocols. We compare training-free approaches, deterministic models, ensembles, and stochastic generative models. Finally, we instantiate the task as an end-to-end monocular RGB-to-floormaps pipeline. FlatLands provides a rigorous testbed for uncertainty-aware indoor mapping and generative completion for embodied navigation.
title FlatLands: Generative Floormap Completion From a Single Egocentric View
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
Image and Video Processing
url https://arxiv.org/abs/2603.16016