🧪 Test?View on arXiv
Real-Time Diffusion Relighting as a Neural Sensor: Closing the Low-Light Domain Gap for Robotic Perception
Author1, Author2, Author3, Author4, Author5
low-light enhancementrobotic perceptiongenerative models
2611.17438
Builder Relevance
19h ago80%
Abstract
The paper presents a method to enhance robotic perception in low-light conditions using a real-time generative neural sensor.
Reality Card
Core Claim
The proposed method achieves a new state-of-the-art performance on the ExDark low-light benchmark with 87.1% mAP and a 100% lap completion rate in a closed-loop autonomous driving simulator.
Method / Result
87.1% mAP on the ExDark low-light benchmark.
Limitations
The reliance on a large-scale image-to-image diffusion model may pose challenges for reproducibility in different environments.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.