ShelfRectNet: Single View Shelf Image Rectification with Homography Estimation

TL;DR

ShelfRectNet is a deep learning framework that accurately rectifies shelf images from a single view by estimating homography, leveraging a ConvNeXt backbone and synthetic data augmentation for robustness.

Contribution

The paper introduces a novel deep learning approach with a ConvNeXt backbone and synthetic homography augmentation for single-view shelf image rectification.

Findings

Achieves a mean corner error of 1.298 pixels on test data.

Demonstrates competitive accuracy and inference speed compared to classical and deep learning methods.

Provides publicly available dataset and code to foster further research.

Abstract

Estimating homography from a single image remains a challenging yet practically valuable task, particularly in domains like retail, where only one viewpoint is typically available for shelf monitoring and product alignment. In this paper, we present a deep learning framework that predicts a 4-point parameterized homography matrix to rectify shelf images captured from arbitrary angles. Our model leverages a ConvNeXt-based backbone for enhanced feature representation and adopts normalized coordinate regression for improved stability. To address data scarcity and promote generalization, we introduce a novel augmentation strategy by modeling and sampling synthetic homographies. Our method achieves a mean corner error of 1.298 pixels on the test set. When compared with both classical computer vision and deep learning-based approaches, our method demonstrates competitive performance in both accuracy and inference speed. Together, these results establish our approach as a robust and efficient solution for realworld single-view rectification. To encourage further research in this domain, we will make our dataset, ShelfRectSet, and code publicly available