Cross-modal semantic scene completion for complex urban traffic scenes with reachability geometric attention

Baorong Zhan, Xichang Yu, Jiajun Zou, Shaojiang Liu, Feng Wang, Meixia Dong · 2026

Read Cross-modal semantic scene completion for complex urban traffic scenes with reachability geometric attention by Baorong Zhan, Xichang Yu, Jiajun Zou, Shaojiang Liu, Feng Wang, Meixia Dong (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-13396651.txt.

Description

Baorong Zhan and others offer cross-sense scene fill for busy city roads in a 2026 study. Cars and walkers hide each other on city roads, and fills that lean on seen bits or block grids alone fail to regrow hid bits pixel by pixel.

Their AGAC net builds a reach map in one frame, casts it on the photo plane, and steers fill only down doable, cheap, straight paths. The decoder regrows pixel sense and shapes for hid zones. Self-drive cars gain a map-wise way to see round blocks, not just guess at them.

Catalog record

CREATORBaorong Zhan, Xichang Yu, Jiajun Zou, Shaojiang Liu, Feng Wang, Meixia Dong
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE64 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13396651

Browse the full library · About the Tower of Babel