Dual-pixel sensors allow a camera to determine the absolute size of an object using defocus blur, eliminating the need for a reference ruler.
Most computer vision systems cannot tell if they are looking at a giant prop or a tiny toy without a known object in the frame. This new method uses the hardware found in many smartphones to measure the real-world scale of objects automatically. By analyzing the subtle blur in dual-pixel data, the system recovers the true 3D structure and size. This practical magic turns standard phone cameras into precision measuring tools for 3D scanning. It has massive implications for augmented reality and robotic navigation where knowing exact distances is essential.
DP-SfM: Dual-Pixel Structure-from-Motion without Scale Ambiguity
arXiv · 2605.01852
Multi-view 3D reconstruction, namely, structure-from-motion followed by multi-view stereo, is a fundamental component of 3D computer vision. In general, multi-view 3D reconstruction suffers from an unknown scale ambiguity unless a reference object of known size is present in the scene. In this article, we show that multi-view images captured using a dual-pixel (DP) sensor can automatically resolve the scale ambiguity, without requiring a reference object or prior calibration. Specifically, the d