Brand Label Albedo Extraction of eCommerce Products using Generative Adversarial Network
This work addresses a domain-specific challenge in e-commerce for improving product visualization, but it is incremental as it builds on existing generative methods for image translation.
The paper tackles the problem of extracting albedo (surface reflectance) from branded labels on e-commerce products under diverse lighting conditions, using a generative adversarial network trained on synthetic data, and reports that it generalizes well to unseen rendered and real-world images compared to existing methods.
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.