elvis · @omarsar0 · X·2026-07-07 06:11·57天前
AI 导读

DAIR.AI 的 Elvis Saravia 推荐了开源视觉基础模型 LingBot-Vision,该模型在长连续操作中实现了深度一致性。同期发布的 LingBot-Depth 2.0 采用 150M 规模训练,深度误差减半,在 12/16 个基准测试中夺冠,解决了玻璃、镜子等透明物体的深度估计难题。LingBot-Vision 完全开源,LingBot-Depth 2.0 也于今日一同发布。

elvis@omarsar0
57AI 编辑部评分,满分 100
2026-07-07 06:11· 57天前
AI 导读

DAIR.AI 的 Elvis Saravia 推荐了开源视觉基础模型 LingBot-Vision,该模型在长连续操作中实现了深度一致性。同期发布的 LingBot-Depth 2.0 采用 150M 规模训练,深度误差减半,在 12/16 个基准测试中夺冠,解决了玻璃、镜子等透明物体的深度估计难题。LingBot-Vision 完全开源,LingBot-Depth 2.0 也于今日一同发布。

Cool open-source release.

Physical AI is the next frontier, so things are shifting from thinking to taking action.

LingBot-Vision looks like a strong visual foundation model and shows progress in consistent depth on long, continuous operations.

Robbyant🪞 Glass. Mirrors. Transparent objects. — The nightmare of every depth camera. We just solved it! Introducing LingBot-Depth 2.0: 150M-scale training, half the d...