LC-HR2FNet: High-Resolution Early-Level Fusion-Based LiDAR-Camera Network for Accurate Road Segmentation Autonomous Driving
Lele Wang, Ming Li, Peng Zhang · 2026
Read LC-HR2FNet: High-Resolution Early-Level Fusion-Based LiDAR-Camera Network for Accurate Road Segmentation Autonomous Driving by Lele Wang, Ming Li, Peng Zhang (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-13258881.txt.
Description
Lele Wang, Ming Li, and Peng Zhang fuse laser and camera data for road surface mapping in a 2026 driving perception paper. Sparse laser points were converted into dense image like maps and joined with color photos early in processing. A high resolution network then kept fine boundary detail through later stages.
Boundary confusion from weak context modeling motivated the design. Multi scale confidence gathering decided each pixel class at the end. Benchmark tests on a standard road dataset reached top tier scores across city scenes. Performance held across varied urban layouts in the test set. Self driving developers get an early fusion design that preserves thin road edges.
Catalog record
| CREATOR | Lele Wang, Ming Li, Peng Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |