Robbyant/lingbot-map
[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #94 of 2,503 repositories GStars tracks this week (top 4%).
The project lists 3 contributors on GitHub.
Peaked at #3 in the weekly ranking the week of Jul 12, its best in the past year.
Use Cases & Benefits
- Implements a geometric context transformer for efficient streaming 3D reconstruction from video sequences.
- Enables stable, high-speed inference on long sequences using a feed-forward architecture with paged KV cache attention.
- Use for real-time 3D mapping and reconstruction in robotics or autonomous navigation with continuous video input.
- Use for offline batch rendering of large-scale indoor or outdoor scenes from long video walkthroughs.
- Use for research and benchmarking on diverse 3D reconstruction datasets like KITTI, Oxford Spires, and Tanks and Temples.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
Watch-outs
- No GitHub releases; pin a commit or tag instead of a release.
General guidance from repository metadata, not legal advice. How we score
From the README
PyTorch 2.8.0 is the recommended version because NVIDIA Kaolin (required by the batch rendering pipeline) has prebuilt wheels for
torch-2.8.0_cu128. If you only needdemo.pyyou may use a newer PyTorch, but the batch renderer then requires building Kaolin from source. For other CUDA versions, see PyTorch Get Started.FlashInfer provides paged KV cache attention for efficient streaming inference. It is a pure-Python package that JIT-compiles CUDA kernels on first use, so a single wheel works across CUDA/PyTorch versions:
--index-url https://pypi.org/simpleis only needed if your default pip index is an internal mirror that doesn't haveflashinfer-python. (Optional) For faster first-use, you can additionally install a CUDA-specific JIT cache:pip install flashinfer-jit-cache -f https://flashinfer.ai/whl/cu128/flashinfer-jit-cache/. See FlashInfer installation for details. If FlashInfer is not installed, the model falls back to SDPA (PyTorch native attention) via--use_sdpa.🚧 Coming soon: we're training an stronger model that supports longer sequences — stay tuned.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+6,126 stars over 89 days across 39 snapshot days; best day +827 on Jul 19.
Forks
2.0K+720
Open issues
85+22
Compared with peers in Backend
Fastest-growing repositories GStars tracks in this cohort for the week of Oct 11, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| DuarteSantos8/openGym | 12.3K | +3.8K | 60 | 5 days ago |
| anthropics/knowledge-work-plugins | 29.8K | +2.4K | 75 | — |
| 666ghj/MiroFish | 79.5K | +2.4K | 23 | 222 days ago |
| microsoft/mxc | 2.8K | +1.3K | 75 | 8 days ago |
| danyuchn/asd-ste100-skill | 4.7K | +1.0K | 75 | — |
| Robbyant/lingbot-map | 18.1K | +856 | 75 | — |
| Category median | 12.3K | +2.4K | 75 | — |
Discover Repositories
Search across tracked repositories by name or description