Amap releases open ABot-Recon streaming 3D model
Alibaba's Amap released ABot-Recon, an open streaming 3D-reconstruction model that processes sequences beyond 10,000 frames with a fixed 12-frame local context.
Why it matters
The release makes long-sequence monocular reconstruction reproducible with bounded runtime and memory, while the corrected record avoids attributing the reported benchmark to an H100 that Amap's release does not name.
Evidence notes
- ABot-Recon accepts monocular RGB video without requiring depth sensors or pre-calibrated camera parameters.
- On KITTI-02 at 504 by 280 resolution, ABot-Recon reaches 24.45 frames per second with about 6.71 GB peak memory; the stated minimum GPU is a GTX 1080 Ti.
- Inference code, evaluation scripts and pretrained weights were public at announcement; no future training-code release is treated as completed.