PnP-Net: A hybrid Perspective-n-Point Network

TL;DR

PnP-Net introduces a hybrid deep learning and model-based approach to robustly estimate camera pose from 3D-2D point correspondences, effectively handling mismatches and noise with low computational cost.

Contribution

The paper presents PnP-Net, a novel hybrid method combining deep learning and classical algorithms for robust and efficient pose estimation in challenging scenarios.

Findings

Successfully handles mismatched correspondences and noise.

Achieves accurate pose estimation with low and fixed computational complexity.

Demonstrates superior performance on synthetic and real-world data.

Abstract

We consider the robust Perspective-n-Point (PnP) problem using a hybrid approach that combines deep learning with model based algorithms. PnP is the problem of estimating the pose of a calibrated camera given a set of 3D points in the world and their corresponding 2D projections in the image. In its more challenging robust version, some of the correspondences may be mismatched and must be efficiently discarded. Classical solutions address PnP via iterative robust non-linear least squares method that exploit the problem's geometry but are either inaccurate or computationally intensive. In contrast, we propose to combine a deep learning initial phase followed by a model-based fine tuning phase. This hybrid approach, denoted by PnP-Net, succeeds in estimating the unknown pose parameters under correspondence errors and noise, with low and fixed computational complexity requirements. We demonstrate its advantages on both synthetic data and real world data.