Robbyant, the embodied-AI unit of Ant Group, has released LingBot-Map, an open-source foundation model that reconstructs walkable 3D scenes in real time from ordinary smartphone footage, running locally on a single consumer GPU. The model, published under the permissive Apache 2.0 license, takes a streaming video feed and produces both a point cloud and an estimated camera trajectory in a single feed-forward pass, without the heavy optimization loops that have long constrained earlier reconstruction pipelines.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.