# Towards Better Morphed Face Images without Ghosting Artifacts

arXiv: https://arxiv.org/abs/2312.08111 · HTML: https://mlsanity.com/paper/2312.08111/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 48 references that are in the map.
- First posted on arXiv 13 Dec 2023.

## Builds on (most cited first, 8 of 8)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Detecting and Simulating Artifacts in GAN Fake Images](https://mlsanity.com/paper/1907.06515/) (2019)
- [Deep Face Representations for Differential Morphing Attack Detection](https://mlsanity.com/paper/2001.01202/) (2020)
- [Are GAN-based Morphs Threatening Face Recognition?](https://mlsanity.com/paper/2205.02496/) (2022)
- [Reflection Analysis for Face Morphing Attack Detection](https://mlsanity.com/paper/1807.02030/) (2018)
- [Style Your Face Morph and Improve Your Face Morphing Attack Detector](https://mlsanity.com/paper/2004.11435/) (2020)

## Built on by (most cited first, 1 of 1)

- [Deceptive Beauty: Evaluating the Impact of Beauty Filters on Deepfake and Morphing Attack Detection](https://mlsanity.com/paper/2509.14120/) (2025)

## Abstract (arXiv)

Automatic generation of morphed face images often produces ghosting artifacts due to poorly aligned structures in the input images. Manual processing can mitigate these artifacts. However, this is not feasible for the generation of large datasets, which are required for training and evaluating robust morphing attack detectors. In this paper, we propose a method for automatic prevention of ghosting artifacts based on a pixel-wise alignment during morph generation. We evaluate our proposed method on state-of-the-art detectors and show that our morphs are harder to detect, particularly, when combined with style-transfer-based improvement of low-level image characteristics. Furthermore, we show that our approach does not impair the biometric quality, which is essential for high quality morphs.