Year: 2025
Type: article
Abstract: This paper analyzes common pitfalls encountered during video GAN training and explores methods to mitigate them through hybrid loss functions. We focus on combining adversarial, pixel-wise reconstruction, perceptual, and temporal consistency losses to stabilize learning and improve the realism and coherence of generated video. An empirical study compares several loss configurations on a human action video dataset, using PSNR, LPIPS, FVD, and a custom temporal consistency metric. Results show that adding reconstruction and perceptual losses enhances fidelity and detail, while temporal loss reduces flicker and motion artifacts. The proposed hybrid loss has achieved balanced gains in fidelity and temporal stability
Authors: Mykola Maksymiv, Taras Rak
Institutions: Lviv Polytechnic National University, IT Step University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4411230906