Skip to content

intsystems/2026-Project-208

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

39 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Conditional Generative Drifting for One-Step One-to-Many Super-Resolution

License GitHub Contributors GitHub Issues GitHub Pull Requests

Author Kseniia Ibragimova
Supervisor Andrei Filatov

Assets

Abstract

This work investigates the applicability of the Generative Drifting framework to one-step image super-resolution in the one-to-many setting. A single low-resolution image may correspond to multiple plausible high-resolution reconstructions, yet most efficient super-resolution methods are trained deterministically and therefore tend to produce averaged, over-smoothed outputs. To address this limitation, we explore the Generative Drifting paradigm, which models generation through a learned drift field and enables single-step inference. We propose a conditional stochastic formulation that learns a direct mapping from a low-resolution image and noise to plausible high-resolution images in a single forward pass. The proposed method defines drifting in residual feature space, encouraging generated samples to move toward plausible high-resolution targets while preventing collapse to a single solution. Experiments evaluate reconstruction quality, perceptual realism, and diversity using PSNR, SSIM, LPIPS, and one-to-many consistency metrics.

Keywords

Generative Drifting, Super-Resolution, One-Step Generation

Licence

Our project is MIT licensed. See LICENSE for details.

About

No description or website provided.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Generated from kisnikser/m1p-template