Newest papers

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

Ariel Lapid, Yuval Haitman, Reuven Peretz, Arnon Netzer, Idit Diamant · 2026 · arXiv

DOI: 10.48550/arXiv.2610.31222 · open-access PDF

Spanish

La mejora de imagen de baja luz (LLIE) tiene como objetivo recuperar imágenes bien expuestas y perceptualmente fieles de observaciones severamente degradadas. Los métodos generativos recientes basados en la difusión logran una fuerte calidad perceptiva aprovechando poderosos previos de imagen, pero su muestreo iterativo incurre en un coste computacional sustancial, limitando la implementación práctica. A pesar de los recientes ganancias de eficiencia en la generativa LLIE, la mejora de alta calidad con una evaluación de función única y un cálculo general bajo sigue siendo un desafío, especialmente bajo diversas condiciones de baja iluminación en el mundo real.

Machine translation (Meta M2M100); the English original follows.

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 l

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31222, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange