Skip to content
AI News HubLIVE
Original source2 min read

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

Summary

The paper proposes embedding a generative neural sensor within the control loop, treating illumination as a generative prior and decoupling high-latency semantic recovery from low-latency control. It achieves 87.1% mAP on ExDark and 100% lap completion in CARLA.

SourcearXiv Computer VisionAuthor: Shengjie Xu, Alexander Gao, Anshul Rai, Dae Yeol Lee, Guan-Ming Su, Ming C. Lin
Real-Time Diffusion Relighting as a Neural Sensor: Closing the Low-Light Domain Gap for Robotic Perception
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 12 Nov 2026]

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

View a PDF of the paper titled Real-Time Diffusion Relighting as a Neural Sensor: Closing the Low-Light Domain Gap for Robotic Perception, by Shengjie Xu and 5 other authors

View PDF HTML (experimental)

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.

Comments: 8 pages, 5 figures. Accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2026. Project page: this https URL

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2611.17438 [cs.CV]

(or arXiv:2611.17438v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.17438

arXiv-issued DOI via DataCite (pending registration)

Journal reference: 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Pittsburgh, PA, USA, 2026, pp. 12703-12710

Submission history

From: Shengjie Xu [view email] [v1] Thu, 12 Nov 2026 19:10:40 UTC (4,916 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Real-Time Diffusion Relighting as a Neural Sensor: Closing the Low-Light Domain Gap for Robotic Perception, by Shengjie Xu and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Embeds a generative neural sensor in the control loop, using a diffusion model as an illumination prior for task-relevant semantic recovery
  • Proposes a real-time perceptual architecture that runs a large image-to-image diffusion model in a background thread, activated only on detection confidence drops
  • Achieves new state-of-the-art 87.1% mAP on the ExDark low-light benchmark and boosts detection under adverse weather
  • Demonstrates 100% lap completion in the CARLA closed-loop driving simulator, integrating high-latency generative models with standard robotic control stacks

Highlights and analysis are generated automatically and may contain errors. Check the original source.