Brand Label Albedo Extraction of eCommerce Products using Generative Adversarial Network

TL;DR

This paper introduces a method to extract albedo of branded labels on e-commerce products using synthetic data generation and generative adversarial networks, demonstrating strong generalization to real-world images.

Contribution

The paper presents a novel approach combining synthetic data and GANs for albedo extraction, improving generalization to in-the-wild images.

Findings

Method generalizes well to unseen images

Synthetic dataset effectively trains the model

Outperforms existing methods in real-world scenarios

Abstract

In this paper we present our solution to extract albedo of branded labels for e-commerce products. To this end, we generate a large-scale photo-realistic synthetic data set for albedo extraction followed by training a generative model to translate images with diverse lighting conditions to albedo. We performed an extensive evaluation to test the generalisation of our method to in-the-wild images. From the experimental results, we observe that our solution generalises well compared to the existing method both in the unseen rendered images as well as in the wild image.