@heyshrutimishra: Nobody talks about this but every robot on the market is blind to glass. Put a mirror in front of it. A glass bottle. I…
Summary
LingBot-Depth 2.0, trained on 150M samples, solves the longstanding problem of robots being blind to glass and transparent objects, achieving top performance on 12/16 depth benchmarks and halving depth error. Ant Group used it to significantly improve their robots' perception.
View Cached Full Text
Cached at: 07/06/26, 10:22 PM
Nobody talks about this but every robot on the market is blind to glass. Put a mirror in front of it. A glass bottle. It just… fails.
LingBot-Depth 2.0 trained on 150M samples to fix exactly that. 12 of 16 depth benchmarks, first place. Error cut in half.
Ant Group just 50x’d their robot’s eyes in one generation.
Robbyant (@robbyant_brain): 🪞 Glass. Mirrors. Transparent objects. — The nightmare of every depth camera. We just solved it! Introducing LingBot-Depth 2.0: 150M-scale training, half the depth error, 12/16 benchmarks topped. Powered by LingBot-Vision — the visual foundation model behind Depth’s
Similar Articles
@rohanpaul_ai: The robot’s “eyes” just received a big upgrade. LingBot-Depth 2.0, a depth-completion model with half the depth error j…
LingBot-Depth 2.0 is a depth-completion model that halves depth error, excels on transparent objects like glass and mirrors, and tops 12 out of 16 benchmarks, powered by the open-source LingBot-Vision backbone.
@AdinaYakup: LingBot Vision A self-supervised vision backbone family for dense spatial perception from Ant Group @robbyant_brain - A…
LingBot Vision, a self-supervised vision backbone family from Ant Group, uses masked boundary modeling to achieve state-of-the-art performance on dense spatial perception tasks, beating the larger DINOv3 model on NYU-Depth v2.
@rohanpaul_ai: A 1B-parameter vision model just beat a 7B one on depth, frozen, single linear layer, zero fine-tuning. @robbyant_brain…
Robbyant releases LingBot-Vision, a 1B-parameter vision model trained on boundaries that achieves better depth estimation than DINOv3-7B, with open weights.
@heyshrutimishra: AGIBOT’s robot just made me a drink. Flawlessly. Ice in the glass, drink poured, bottle shaken, cherry dropped on top. …
AGIBOT's humanoid robot flawlessly made a drink, showcasing precise manipulation. The three-year-old company has shipped 5,000 robots this quarter, focusing on perfecting movements before speed.
To a depth camera, a glass wall is basically empty space. This model fills it back in.
A model is proposed to fill in missing depth data from depth cameras when encountering transparent surfaces like glass walls, addressing a common sensor limitation.