Robbyant/lingbot-map

LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction Robbyant Team [](https://linzhuo.xyz/gct.pdf) [](https://arxiv.org/abs/2604.14141) [](https://technology.robbyant.com/lingbot-map) [](https://huggingface.co/robbyant/lingbot-map) [](https://www.modelscope.cn/models/Robbyant/lingbot-map) [](LICENSE.txt) https://github.com/user-attachments/assets/fe39e095-af2c-4ec9-b68d-a8ba97e505ab LingBot-Map has focused on: Click to expand 1. Create conda environment 2. Install PyTorch (CUDA 12.8) 3. Install lingbot-map 4. Install FlashInfer (recommended) 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: 5. Visualization dependencies (optional) After installation, run your first scene with one command: This launches an interactive viser viewer at http://localhost:8080. See Interactive Demo below for the full set of scenes and flags, or jump to Offline Rendering Pipeline for long-sequence batch rendering. Run demo.py for interactive 3D visualization via a browser-based viser viewer (default http://localhost:8080). We provide three example scenes in example/ that you can run out of the box: https://github.com/user-attachments/assets/aa10f7ab-8024-43c7-92f8-d56159ec85c8 https://github.com/user-attachments/assets/212a1744-6ff5-4ccf-9bd4-728608248b57 https://github.com/user-attachments/assets/5ae0a292-b081-40c6-838c-b7c1a0538d75 Sequence is too long for the…