amap-cvlab/ABot-Recon
Streaming 3D reconstruction from only video input: Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction
About the project
ABot-Recon is a streaming 3D reconstruction model that uses a fixed 12-frame local context per step, predicting a point map and adjacent relative pose, then composing them into a global trajectory and point cloud.
Useful for
- Reconstruct camera trajectory and point cloud from a long video sequence
- Run GPU inference via the Python API or demo.py with the released checkpoint
- Refine trajectory on revisited scenes using optional loop closure
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 12 stars so far today, about 17 expected by the end of the day.
- The repository is 22 days old and already has 887 stars.
- Top new repositories this month: #98.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 887
- Stars in a day
- 17
- Forks
- 60
- Issues and pull requests
- 6
- Watchers
- 4
- Language
- Python
- License
- Apache-2.0
- Created
- August 27, 2026
- Last push
- September 16, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 18, 2026Top new repositories this month: #93
- September 17, 2026Top new repositories this month: #99
Similar projects
-
5.4
anthropics/uplifting-biomolecular-modeling
A reference collection of 36 drop-in optimization kits for the inference paths of open protein- and genomics-ML tools, from structure prediction to protein language models. Each kit speeds up a pinned upstream release…
-
4.6
SpikeCalls/FlyDrones
Turns a fruit fly connectome (MaleCNS, 166k neurons) into a drone pilot: camera → visual neurons → spiking network → descending neurons → drone commands. Browser demo runs with no install.
-
4.6
niedachu/MateriaSim
MateriaSim is a Python framework for reproducible molecular simulation of multi-component materials: it organizes configurations, studies and runs on top of GROMACS with input validation and result traceability.
-
3.9
TheJustinSunPrize/awards
Public repository for the Justin Sun Prize: rules, a bank of 1,022 math problems, candidates, awards, and formal verification evidence in machine-readable form.
-
2.9
anonymous-report-421/GPT-as-Policy
Evaluation code and a bilingual technical report assessing GPT 6 Astra as an embodied policy on ten RoboDojo tasks, including a hybrid scheme that corrects π₀.₅ actions.
-
1.8
alextitonis/fly.ai
A simulation of the complete central nervous system of a fruit fly (166,700 neurons, 25.6M connections) from the MaleCNS v1.0 connectome, used as a frozen reservoir without training.