Single image calibration using knowledge distillation approaches

TL;DR

This paper introduces a novel incremental learning approach for single-image camera calibration using knowledge distillation, enabling CNNs to adapt to new data while retaining prior knowledge, thus improving generalization and efficiency.

Contribution

It adapts four incremental learning strategies to a CNN for camera calibration, addressing generalization and resource constraints in a novel way.

Findings

BiC outperforms other methods in calibration accuracy

Incremental learning maintains performance on new and old data

Approach reduces computational and space requirements

Abstract

Although recent deep learning-based calibration methods can predict extrinsic and intrinsic camera parameters from a single image, their generalization remains limited by the number and distribution of training data samples. The huge computational and space requirement prevents convolutional neural networks (CNNs) from being implemented in resource-constrained environments. This challenge motivated us to learn a CNN gradually, by training new data while maintaining performance on previously learned data. Our approach builds upon a CNN architecture to automatically estimate camera parameters (focal length, pitch, and roll) using different incremental learning strategies to preserve knowledge when updating the network for new data distributions. Precisely, we adapt four common incremental learning, namely: LwF , iCaRL, LU CIR, and BiC by modifying their loss functions to our regression problem. We evaluate on two datasets containing 299008 indoor and outdoor images. Experiment results were significant and indicated which method was better for the camera calibration estimation.