深度补全模型 LingBot-Depth 2.0 发布，专攻玻璃、镜面、透明物体等传统深度相机失效的场景。训练数据从 3M 扩展到 150M（50 倍），在 12/16 个深度补全基准中排名第一，最难室内场景 RMSE 从 0.132 降至 0.062（误差减半）。模型基于视觉基础模型 LingBot-Vision 构建，后者已完全开源，训练时利用物体边缘几何信息且无需人工边界标签。
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.
🪞 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 breakthrough. Both released today. LingBot-Vision is fully open-sourced. 🧵👇 #Robotics #DepthEstimation #OpenSource #EmbodiedAI在 X 查看被引用的帖子
来源：Rohan Paul · x.com