cs.CVNov 12, 2026

Real-Time Diffusion Relighting as a Neural Sensor: Closing the Low-Light Domain Gap for Robotic Perception

Authors: Shengjie Xu, Alexander Gao, Anshul Rai, Dae Yeol Lee, Guan-Ming Su, Ming C. Lin

Organizations: University of Maryland, College Park · Dolby Laboratories

Abstract

Low-light conditions severely degrade robotic perception: object detectors trained on daylight imagery are prone to failure under dark and adverse weather conditions that fall outside of their training distribution. Furthermore, from an efficiency standpoint, existing Low-Light Image Enhancement (LLIE) methods are designed for offline processing and are therefore impractical to integrate into live control loops. To address these issues, we propose to embed a Generative Neural Sensor within the control loop that treats illumination as a generative prior rather than a signal processing problem, enabling task-relevant semantic recovery. We further propose an Real-Time Perceptual Architecture that decouples high-latency semantic recovery from low-latency robotic control. Rather than blocking the control loop, our system runs a large-scale image-to-image diffusion model in a background thread, and is activated only when a drop in detection confidence signals a perceptual uncertainty event, significantly reducing computational overhead. Our method sets a new state-of-the-art performance on the ExDark low-light benchmark with 87.1% mAP, and under adverse weather conditions, significantly boosts detection rates over competing methods. On a navigation task in a closed-loop autonomous driving simulator (CARLA), we achieve a 100% lap completion rate, establishing a simulation-based proof-of-concept for integrating high-latency generative models with standard robotic control autonomy stacks.

Figures & tables

Explore similar work

CardsList
  1. ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement

    May 25, 2026Yufeng Yang, Jianzhuang Liu, Jisheng Chu +4Image EnhancementLow-Light Image Enhancement

  2. LiDAS: Lighting-driven Dynamic Active Sensing for Nighttime Perception

    Dec 9, 2025Simon de Moreau, Andrei Bursuc, Hafid El-Idrissi +1Autonomous Driving PerceptionActive Sensing

  3. Cyclops: LiDAR as a Camera That Dreams in Color

    Aug 17, 2026Wei Gao, Jian Shu, Mingle Zhao +4Conditional Image GenerationAutonomous Driving Perception