Homographic Navigation: Geometry-Driven Camera Guidance for Deterministic Planar Capture
This work addresses the problem of precise planar capture for computer vision applications, offering a method that reduces supervision requirements while improving accuracy.
The authors propose a geometry-driven framework for guiding camera acquisition to precisely capture planar regions, using homography as an organizing variable. Their method achieves accurate planar alignment from minimal supervision, with a two-pass inference scheme and Stable Warp training strategy improving precision.
We present homographic navigation, a geometry-centric framework for guiding camera acquisition toward precise capture of planar regions. Rather than treating homography as an output, we use it as an organizing variable that unifies learning, alignment, and evaluation. From a single annotated reference image, we generate unlimited synthetic training data via homographic augmentation and train a single-shot model for joint recognition and localization of multiple artifacts (physical objects with a rectangular planar target) through sparse keypoint prediction. To address precision under limited model input resolution, we introduce a two-pass inference scheme with global detection followed by localized refinement, and a Stable Warp training strategy that significantly improves accuracy, particularly in the high-precision regime. The model also predicts confidence estimates per predicted keypoint and per the whole sample. Experimental results demonstrate that accurate planar alignment can be achieved from minimal supervision, providing a foundation for geometry-driven camera guidance and future learning from in-the-wild video data.