GitHub repositories · October 2026
monthly · 30d window · GitHub repositories
All github repositories editions →+212.8%
328 → 1,026 stars
amap-cvlab/ABot-Recon
ABot-Recon is a model and codebase for streaming 3D reconstruction from video input. At each time step it caches features from preceding frames, predicts a point map in the current camera coordinate system, and estimates adjacent relative pose, recovering a global trajectory and point cloud through sequential pose composition. This local design keeps memory and per-frame computation independent of sequence length, with optional loop-closure-based trajectory refinement.
- Appearances
- 1
- Categories
- 1
- First seen
- 1 October 2026
- Latest
- 1 October 2026
Recorded measurements
Published observations only. Missing dates are not zero, and points do not establish what happened between observations. Each source and unit is shown separately.
GitHub repositories · stars
GitHub repositories · 2 dated measurements
Latest value shown: 1,026 stars ·
Higher values appear higher on the chart. The scale covers the recorded values.
View 2 exact dated values and published evidence
| Measured on | Value (stars) | Published in |
|---|---|---|
| 328 | ||
| 1,026 |
“Measured on” uses the original observation date. “Published in” links to the edition that reported it; the dates may differ.
01/
Appearance history
1 appearanceThis page records every appearance of the same entity in the reviewed RiseFinder exports. Rankings keep the original category, period and measurement direction.
If you investigated this riser, tell us what helped—or what was missing.
Share feedback →02/
Get email updates
Join the listGet early signals on the websites, apps, repositories and startups gaining momentum. Join the list for Risefinder email briefings.
By subscribing, you ask us to store your email and send Risefinder updates. You can unsubscribe at any time. Privacy.
Want a sample first? Read past daily emails.