Structural-Prior Deep Learning Network for Millimeter-Wave Radar Image Enhancement in Autonomous Driving Road Sensing

Hongyan Chen, Tonghui Huang, Yuexia Wang, Jiajia Shi, Zhihuo Xu · 2026

Read Structural-Prior Deep Learning Network for Millimeter-Wave Radar Image Enhancement in Autonomous Driving Road Sensing by Hongyan Chen, Tonghui Huang, Yuexia Wang, Jiajia Shi, Zhihuo Xu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13210454.txt.

Description

Hongyan Chen and four co-authors clean up radar images for self-driving cars, in this 2026 paper. Millimeter-wave radar sees through rain and fog, which cameras and lasers cannot. But radar pictures suffer speckle noise that breaks up road edges and hides targets. The team built a deep learning network guided by the scene's structure.

First, an adaptive threshold step extracts the strong scattering skeleton of the scene, giving the network a rough structural map. Attention blocks then rebuild detail at several scales while damping the noise. A custom loss balances three goals: noise removal, smoothness, and edge preservation. On synthetic and real radar sets the method beat filters and rival networks on standard quality scores, and it ran in about twelve milliseconds per frame. The authors aim it at real-time road sensing.

Catalog record

CREATORHongyan Chen, Tonghui Huang, Yuexia Wang, Jiajia Shi, Zhihuo Xu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE56 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13210454

Browse the full library · About the Tower of Babel