Paper Detail

GLOW-FM: Efficient Generative Low-Light Image Enhancement with One-Step Latent Flow Matching

Ariel Lapid, Yuval Haitman, Reuven Peretz, Arnon Netzer, Idit Diamant

huggingface Score 9.5

Published 2026-10-22 · First seen 2026-11-02

General AI

Abstract

Low-light image enhancement (LLIE) aims to recover well-exposed and perceptually faithful images from severely degraded observations. Recent diffusion-based generative methods achieve strong perceptual quality by leveraging powerful image priors, but their iterative sampling incurs substantial computational cost, limiting practical deployment. Despite recent efficiency gains in generative LLIE, high-quality enhancement with a single function evaluation and low overall computation remains challenging, particularly under diverse real-world low-light conditions. We introduce GLOW-FM, a one-step latent flow-matching framework for efficient generative LLIE. GLOW-FM performs conditional transport in the latent space of a frozen Tiny-VAE and leverages Terminal Velocity Matching (TVM) to enable enhancement with a single function evaluation. Matched comparisons with alternative one-step objectives support TVM as an effective design choice, and, to the best of our knowledge, this is its first adaptation to image restoration and specifically to LLIE. Extensive experiments on challenging real-world benchmarks demonstrate that GLOW-FM achieves competitive image quality and state-of-the-art cross-dataset generalization while requiring only a single function evaluation and 34 GFLOPs for the small variant. These findings highlight the potential of GLOW-FM to bring generative LLIE closer to practical deployment through single-step inference and compact latent modeling. Code will be made publicly available upon publication.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{lapid2026glow,
  title = {GLOW-FM: Efficient Generative Low-Light Image Enhancement with One-Step Latent Flow Matching},
  author = {Ariel Lapid and Yuval Haitman and Reuven Peretz and Arnon Netzer and Idit Diamant},
  year = {2026},
  abstract = {Low-light image enhancement (LLIE) aims to recover well-exposed and perceptually faithful images from severely degraded observations. Recent diffusion-based generative methods achieve strong perceptual quality by leveraging powerful image priors, but their iterative sampling incurs substantial computational cost, limiting practical deployment. Despite recent efficiency gains in generative LLIE, high-quality enhancement with a single function evaluation and low overall computation remains challen},
  url = {https://huggingface.co/papers/2610.31222},
  keywords = {low-light image enhancement, diffusion-based generative methods, latent flow-matching, Tiny-VAE, Terminal Velocity Matching, single function evaluation, cross-dataset generalization, code available, huggingface daily},
  eprint = {2610.31222},
  archiveprefix = {arXiv},
}

Metadata

{}