Get Started
Home
Topics
Search
Library
Research questionHow can indoor navigation infer a complete metric traversability map from a single egocentric image?A single egocentric image reveals only a small portion of the surrounding floor, while navigation requires a spatially metric map of traversable space. Regions outside the view are ambiguous and must be inferred from limited visual evidence.
AI
Computer Vision
Evaluation & Benchmarks
Image & Video Processing
Machine Learning
Robotics
Latest papersRecent research connected to this question, newest first.FlatLands: Generative Floormap Completion From a Single Egocentric ViewThe source presents FlatLands, a benchmark with 270,575 observations from 17,656 real metric indoor scenes, aligned observations and bird’s-eye-view maps, and in- and out-of-distribution protocols. Its evidence covers single-view floor-map completion and an end-to-end monocular RGB-to-floormaps pipeline, rather than broader deployed-navigation performance.research paper · Sep 2, 2026
Related questions
How can we predict local 3D occupancy from a single underwater RGB image despite unreliable visual geometry?How can indoor robots prevent glare-corrupted RGB-D measurements from creating phantom obstacles in navigation costmaps?How can inertial measurements recover metric scale in pretrained monocular 3D predictions?How can single-image depth estimation resolve scale ambiguity to produce consistent metric depth across environments?