ๆœบๅ™จไน‹ๅฟƒ JIQIZHIXIN (@jiqizhixin)

2026-02-01 | โค๏ธ 172 | ๐Ÿ” 22


What if your robot or car could see depth more clearly than a top-tier RGB-D camera?

Researchers from Ant Group present LingBot-Depth.

It treats sensor errors as โ€œmaskedโ€ clues, using visual context to intelligently fill in and refine incomplete depth maps.

It outperforms leading hardware in both precision and coverage, creating a unified understanding of color and depth for robotics and autonomous driving.

Masked Depth Modeling for Spatial Perception

Project: https://t.co/S7wPdrTmr4 HuggingFace: https://t.co/8GrF45wM2i Paper: https://t.co/bjiWl9TvUn

Our report: https://t.co/aE1Lj0DU3j

๋ฏธ๋””์–ด

image


Tags

3D-Vision avatar autonomous