/TECHStory update pending

LingBot releases visual foundation and depth-completion models to help robots map glass and reflective surfaces

LingBot-Depth 2.0 halves depth estimation error using 150 million training samples.

Story Brief

LingBot-Depth 2.0 halves depth estimation error using 150 million training samples.

Commentary on X

Highest ranked

@rohanpaul_ai Relying on self-supervised boundary training instead of human labels is a brilliant strategy for long-term scalability. It ensures that the general vision backbone can continue to improve rapidly without a data collection bottleneck.

Eclipse 🌖@ECLresearchTECH

View all

Rohan Paul@rohanpaul_aiTECH

The robot’s “eyes” just received a big upgrade. LingBot-Depth 2.0, a depth-completion model with half the depth error just dropped. 12/16 benchmarks topped. Glass, mirrors, and transparent objects are so easy for us humans, but so hard for robots, because they do not behave like ordinary surfaces in a camera pipeline. A robot that misunderstands a balcony window or a table edge, will have a completely false planning inside a false world. Huge implecation. LingBot-Depth 2.0 takes an RGB image plus a broken depth map from a sensor and then outputs a cleaner depth map and a usable 3D point cloud. Numbers on LingBot-Depth 2.0 - Excels on glass, mirrors & transparent objects — where traditional depth cameras fail - Training data: 3M → 150M (50x scale-up) - 12 out of 16 first-place rankings on depth completion benchmarks - RMSE cut in half: 0.132 → 0.062 on the hardest indoor scenes LingBot-Vision trained on boundaries, because object edges carry the geometry robots need. No human boundary labels are used, which makes this approach easier to scale. The open-sourced LingBot-Vision is the general vision backbone, and LingBot-Depth 2.0 is the depth model built on it.