Image Semantic Transformation: Faster, Lighter and Stronger

TL;DR

This paper introduces ISTRC, a novel model that uses FaceNet's Euclidean latent space to perform semantic image transformations and reconstructions efficiently, enabling high-level manipulations with minimal training time.

Contribution

The paper presents ISTRC, a new approach leveraging FaceNet's latent space for semantic image transformations and perfect reconstructions, with rapid training and high accuracy.

Findings

Performs 10 high-level semantic transformations

Achieves perfect image reconstruction within the circle

Requires only 3 hours of training on GTX 1080

Abstract

We propose Image-Semantic-Transformation-Reconstruction-Circle(ISTRC) model, a novel and powerful method using facenet's Euclidean latent space to understand the images. As the name suggests, ISTRC construct the circle, able to perfectly reconstruct images. One powerful Euclidean latent space embedded in ISTRC is FaceNet's last layer with the power of distinguishing and understanding images. Our model will reconstruct the images and manipulate Euclidean latent vectors to achieve semantic transformations and semantic images arthimetic calculations. In this paper, we show that ISTRC performs 10 high-level semantic transformations like "Male and female","add smile","open mouth", "deduct beard or add mustache", "bigger/smaller nose", "make older and younger", "bigger lips", "bigger eyes", "bigger/smaller mouths" and "more attractive". It just takes 3 hours(GTX 1080) to train the models of 10 semantic transformations.