# Parallax-Tolerant Weakly-Supervised Pixel-Wise Deep Color Correction for Image Stitching of Pinhole Camera Arrays

## TL;DR

This paper introduces a new method for stitching images from pinhole camera arrays that reduces visible artifacts caused by parallax and color differences.

## Contribution

A parallax-tolerant, weakly supervised deep color correction framework for image stitching in pinhole camera arrays is proposed.

## Key findings

- The proposed framework effectively compensates for color differences in overlapping regions using a dynamic loss weight network.
- A gradient-based MRF strategy harmonizes non-overlapping regions with overlapping ones, improving overall image quality.
- The new evaluation metric, Color Differences Across the Seam, quantitatively shows improved naturalness in stitched images.

## Abstract

Camera arrays typically use image-stitching algorithms to generate wide field-of-view panoramas, but parallax and color differences caused by varying viewing angles often result in noticeable artifacts in the stitching result. However, existing solutions can only address specific color difference issues and are ineffective for pinhole images with parallax. To overcome these limitations, we propose a parallax-tolerant weakly supervised pixel-wise deep color correction framework for the image stitching of pinhole camera arrays. The total framework consists of two stages. In the first stage, based on the differences between high-dimensional feature vectors extracted by a convolutional module, a parallax-tolerant color correction network with dynamic loss weights is utilized to adaptively compensate for color differences in overlapping regions. In the second stage, we introduce a gradient-based Markov Random Field inference strategy for correction coefficients of non-overlapping regions to harmonize non-overlapping regions with overlapping regions. Additionally, we innovatively propose an evaluation metric called Color Differences Across the Seam to quantitatively measure the naturalness of transitions across the composition seam. Comparative experiments conducted on popular datasets and authentic images demonstrate that our approach outperforms existing solutions in both qualitative and quantitative evaluations, effectively eliminating visible artifacts and producing natural-looking composite images.