LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
Robbyant Team
🗺️ Meet LingBot-Map! We've built a feed-forward 3D foundation model for streaming 3D reconstruction! 🏗️🌍
LingBot-Map has focused on:
Geometric Context Transformer: Architecturally unifies coordinate grounding, dense geometric cues, and long-range drift correction within a single streaming framework through anchor context, pose-reference window, and trajectory memory.
High-Efficiency Streaming Inference: A feed-forward architecture with paged KV cache attention, enabling stable inference at ~20 FPS on 518×378 resolution over long sequences exceeding 10,000 frames.
State-of-the-Art Reconstruction: Superior performance on diverse benchmarks compared to both existing streaming and iterative optimization-based approaches.
📑 Table of Contents
📰 News
📋 TODO
⚙️ Installation
📦 Model Download
🚀 Quick Start
🎬 Interactive Demo (demo.py)
Try the Example Scenes
Streaming with Keyframe Interval
Windowed Inference (for long sequences, >3000 frames)
Sky Masking
Visualization Options
Performance & Memory
Try the Example Scenes
Streaming with Keyframe Interval
Streaming with Keyframe Interval
Windowed Inference (for long sequences, >3000 frames)
Windowed Inference (for long sequences, >3000 frames)
Sky Masking
Visualization Options
Performance & Memory
🎥 Offline Rendering Pipeline (demo_render/batch_demo.py)
🎥 Offline Rendering Pipeline (demo_render/batch_demo.py)
📜 License
📖 Citation
✨ Acknowledgments
📰 News
2026-06-28 — Fixed an SDPA KV cache bug. The SDPA backend now performs better on long sequences. We still recommend the FlashInfer backend for the best performance.
2026-05-25 — 📊 Evaluation benchmark released. We released the evaluation scripts for KITTI and Oxford Spires — see benchmark/ for the pipeline, and run preprocess/oxford.py to prepare Oxford Spires data before evaluation.
2026-04-29 — 📹 Long-video demo released. We released a very-long-video example (~25 000 frames, 13-minute indoor walkthrough) rendered with the offline pipeline — see Worked Example for the command, flag rationale, and rendered output.
2026-04-27 — 🚀 LingBot-Map accelerated. Pull the latest main and run python demo.py --compile ... or python gct_profile.py --backend flashinfer --dtype bf16 --compile to verify on your hardware.
2026-04-24 — Fixed a FlashInfer KV cache bug where --keyframe_interval > 1 silently cached non-keyframes. You should now see better pose and reconstruction quality when running with more than 320 frames.
📋 TODO
✅ Release evaluation benchmark
✅ Oxford Spires dataset
✅ KITTI dataset
✅ VBR dataset
✅ Droid-W dataset
✅ TUM-D dataset
✅ 7-scenes dataset
✅ ETH3D dataset
✅ Tanks and Temples dataset
✅ NRGBD dataset
✅ Oxford Spires dataset
✅ KITTI dataset
✅ VBR dataset
✅ Droid-W dataset
✅ TUM-D dataset
✅ 7-scenes dataset
✅ ETH3D dataset
✅ Tanks and Temples dataset
✅ NRGBD dataset
✅ Release demo scripts
✅ Indoor long-video demo (Featured indoor walkthrough)
✅ Outdoor long-video demo
✅ LingBot-World demo (Worked example)
✅ Aerial long-video demo
✅ Indoor long-video demo (Featured indoor walkthrough)
✅ Outdoor long-video demo
✅ LingBot-World demo (Worked example)
✅ Aerial long-video demo
⚙️ Installation
- Create conda environment
- Install PyTorch (CUDA 12.8)
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 need demo.py you may use a newer PyTorch, but the batch renderer then requires building Kaolin from source.
For other CUDA versions, see PyTorch Get Started.
- Install lingbot-map
- 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:
--index-url https://pypi.org/simple is only needed if your default pip index is an internal mirror that doesn't have flashinfer-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.
- Visualization dependencies (optional)
📦 Model Download
🚧 Coming soon: we're training an stronger model that supports longer sequences — stay tuned.
🚀 Quick Start
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.
🎬 Interactive Demo (demo.py)
Run demo.py for interactive 3D visualization via a browser-based viser viewer (default http://localhost:8080).
Try the Example Scenes
We provide four example scenes in example/ that you can run out of the box:
🎯 Featured: indoor walkthrough (~25 000 frames, 13 minutes)
Sequence is too long for the interactive viser viewer — this clip was rendered with the Offline Rendering Pipeline. See that section for the full command.
We will provide more examples in the follow-up.
Streaming with Keyframe Interval
Use --keyframe_interval to reduce KV cache memory by only keeping every N-th frame as a keyframe. Non-keyframe frames still produce predictions but are not stored in the cache. This is useful for long sequences which exceed 320 frames (We train with video RoPE on 320 views, so performance degrades when the KV cache stores more than 320 views. Using a keyframe strategy allows inference over longer sequences.).
Dataset: Download the demo sequences from robbyant/lingbot-map-demo on Hugging Face.
Example run on the travel sequence from the dataset above (sky masking on, 4 camera optimization iterations, keyframe every 2 frames):
Note on inference range. Our method does not perform state resetting by default, so the maximum inference range is bounded by the longest distance seen during training on the dataset. Beyond that distance, state resetting becomes necessary. If you observe pose collapse, switch to windowed mode (--mode windowed) — in most cases tuning --keyframe_interval alone is enough and the rest of the windowed parameters can stay at their defaults.
Windowed Inference (for long sequences, >3000 frames)
Sky Masking
Sky masking uses an ONNX sky segmentation model to filter out sky points from the reconstructed point cloud, which improves visualization quality for outdoor scenes.
Setup:
The sky segmentation model (skyseg.onnx) will be automatically downloaded from HuggingFace on first use.
Usage:
Sky masks are cached in <image_folder>_sky_masks/ so subsequent runs skip regeneration. You can also specify a custom cache directory with --sky_mask_dir, or save side-by-side mask visualizations with --sky_mask_visualization_dir:
Visualization Options
Performance & Memory
Without FlashInfer (SDPA fallback)
Running on Limited GPU Memory
If you run into out-of-memory issues, try one (or both) of the following:
--offload_to_cpu — offload per-frame predictions to CPU during inference (on by default; use --no-offload_to_cpu only if you have memory to spare).
--num_scale_frames 2 — reduce the number of bidirectional scale frames from the default 8 down to 2, which shrinks the activation peak of the initial scale phase.
Faster Inference
Lower the number of iterative refinement steps in the camera head to trade a small amount of pose accuracy for wall-clock speed:
--camera_num_iterations defaults to 4; setting it to 1 skips three refinement passes in the camera head (and shrinks its KV cache by 4×).
🎥 Offline Rendering Pipeline (demo_render/batch_demo.py)
Use this pipeline when your sequence is too long for the interactive viser viewer — for example, the indoor walkthrough featured above. demo_render/batch_demo.py is the all-in-one offline entry point: feed it a video or a folder of images and it will run model inference and produce a headless point-cloud flythrough MP4 in a single command. It shares the same PyTorch / FlashInfer / checkpoint stack as demo.py.
indoor walkthrough featured above
For those constrained by limited VRAM or GPU usage, you may also refer to the implementation at: https://github.com/ureeey/lingbot-map-rtx4060-8g/commit/eeee84a89cc97c1e39b736b46df4ee315275700b
https://github.com/ureeey/lingbot-map-rtx4060-8g/commit/eeee84a89cc97c1e39b736b46df4ee315275700b
Install (extends the main install)
- Rendering Python dependencies
render pulls in open3d>=0.19 and pyyaml (the core numpy<2 constraint comes from the base lingbot-map install). Sky masking in this pipeline uses onnxruntime-gpu for batched segmentation; install it if you don't already have the CPU onnxruntime:
- Kaolin — matches the PyTorch 2.8.0 + CUDA 12.8 recommended above:
--index-url https://pypi.org/simple bypasses any internal mirror that might otherwise serve the PyPI placeholder wheel (which raises ImportError on import).
NVIDIA Kaolin does not publish prebuilt wheels for PyTorch 2.9.x — if you're on 2.9 for other reasons, build Kaolin from source (pip install --no-build-isolation git+https://github.com/NVIDIAGameWorks/kaolin.git, needs local CUDA toolkit). For other torch/CUDA combinations see NVIDIA Kaolin installation.
- ffmpeg
- CUDA extensions (required before first run)
This builds voxel_morton_ext and frustum_cull_ext in place — both are imported by rgbd_render for GPU voxelization and frustum culling.
Worked Example — long indoor walkthrough (~25 000 frames, 13 minutes)
Dataset: Download the example video from robbyant/lingbot-map-demo on Hugging Face.
Flag-by-flag rationale:
Replacing keyframe_interval = 10 with image_stride = 10 speeds up rendering. Then, comment out the camera follow section in demo_render/config/indoor.yaml and set the birdeye's ranges to [2000, 2500] to reproduce the indoor fly-through effect shown in the demo:
Worked Example — outdoor drive scene
Dataset: Download the example video from robbyant/lingbot-map-demo on Hugging Face.
What differs from the indoor walkthrough above:
The remaining flags (--mode windowed --window_size 128, --overlap_keyframes 8, sky-mask caching, overlays, --save_predictions) carry over unchanged from the indoor example — see the flag-by-flag table above.
Worked Example — LingBot-World scenes
Reconstruct videos generated by LingBot-World, our world model — the same pipeline works on generated footage out of the box.
Dataset: Download the example videos (lingbo_world_frames.mp4, lingbo_world2_frames.mp4) from robbyant/lingbot-map-demo on Hugging Face.
For the second clip, run the same command with --video_path /data/demo_videos/lingbo_world2_frames.mp4 --output_folder /data/outputs/lingbo_world2/ (and separate --sky_mask_dir / --sky_mask_visualization_dir folders if you want to keep the cached masks apart).
All flags are identical to the outdoor drive scene above — only the input video and output folder change. See the drive scene and indoor walkthrough tables for the flag-by-flag rationale.
Camera Path (YAML)
The virtual camera path is described by the camera.segments list in the YAML preset passed via --config. Edit the YAML to design your own shot — no need to touch CLI flags.
Built-in presets live in demo_render/config/: default.yaml, indoor.yaml, outdoor_drive.yaml. Copy one and edit the camera: block.
YAML structure
transition controls how many frames are blended between adjacent segments; frames: [0, -1] means "the whole sequence".
Available modes
Single-shot YAML examples
Pure follow (most common):
Full birdeye (good for overview / hero shots):
Follow with birdeye inserts: just list multiple segments in order under segments: — adjacent segments are interpolated using transition frames.
Caveat: when --config loads a YAML preset, passing any segment-shaping CLI flag (--camera_mode, --back_offset, --up_offset, --look_offset, --smooth_window, --follow_scale_frames, --birdeye_start, --birdeye_duration, --reveal_height_mult) discards the YAML's segments and rebuilds the camera path from those flags instead. To stay fully YAML-driven, don't pass any of them on the command line.
Output files
For a given output name (e.g. <scene> or <video_name>):
📜 License
This project is released under the Apache License 2.0. See LICENSE file for details.
📖 Citation
✨ Acknowledgments
We thank Shangzhan Zhang, Jianyuan Wang, Yudong Jin, Christian Rupprecht, and Xun Cao for their helpful discussions and support.
This work builds upon several excellent open-source projects:
VGGT
DINOv2
Flashinfer