Blog Track Poster
Analysing The Spectral Biases in Generative Models
Amitoj Miglani · Shweta Singh · Vidit Aggarwal
Hall 3 + Hall 2B #522
Abstract:
Diffusion and GAN models have demonstrated remarkable success in synthesizing high-quality images propelling them into various real-life applications across different domains. However, it has been observed that they exhibit spectral biases that impact their ability to generate certain frequencies and makes it pretty straightforward to distinguish real images from fake ones. In this blog we analyze these models and attempt to explain the reason behind these biases.
Chat is not available.