Work

Fast-DiM: Towards Fast Diffusion Morphs

Year: 2024

Type: article

Abstract: Diffusion morphs (DiM) create high-quality face morphs; however, they require a high number of network function evaluations (NFE) to create them. We propose a new DiM pipeline, Fast-DiM, which can create morphs of a similar quality but with fewer NFE.

Source: IEEE Security & Privacy

DOI: 10.1109/msec.2024.3410112

Authors: Zander W. Blasingame, Chen Liu

Institution: Clarkson University

Language: English

Topic: Generative Adversarial Networks and Image Synthesis

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Science Foundation

Award: I/UCRC Phase II: I/UCRC for Identification Technology Research