# lingbot-map-3d-reconstruction

A skill for streaming 3D scene reconstruction from images or video: point clouds, camera poses, depth maps. Useful when you need geometry out of a long frame sequence.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 418 installs · ★ 88
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/lingbot-map-3d-reconstruction/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/lingbot-map-3d-reconstruction

## What it does

The skill wires the LingBot-Map model into your agent. Inference is feed-forward, so there is no iterative optimization step. You get a point cloud with per-point confidence, camera poses and depth maps. Under the hood sits a Geometric Context Transformer, and paged KV cache attention keeps long sequences workable: the description claims around 20 FPS at 518×378 across sequences past 10,000 frames.

Everything runs through `demo.py`. Point it at a folder of images with `--image_folder` or at a video with `--video_path` plus `--fps`. For outdoor footage add `--mask_sky`. Long runs have `--keyframe_interval` to store every Nth frame, and a windowed path via `--mode windowed --window_size 64`. The demo serves an interactive viewer in the browser on `localhost:8080`.

Before you start, set up Python 3.10, PyTorch for CUDA 12.8, and download the checkpoint from HuggingFace or ModelScope. FlashInfer for fast attention is a separate install; without it you fall back to `--use_sdpa`. If FlashInfer will not build, the demo still runs, just slower — worth checking against your CUDA version before feeding it a long video.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill lingbot-map-3d-reconstruction -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/lingbot-map-3d-reconstruction/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/lingbot-map-3d-reconstruction/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill lingbot-map-3d-reconstruction -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/lingbot-map-3d-reconstruction/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill lingbot-map-3d-reconstruction -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/lingbot-map-3d-reconstruction/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/trending-skills lingbot-map-3d-reconstruction
```

2. **Manually: put the files in place**
- File: `.github/skills/lingbot-map-3d-reconstruction/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill lingbot-map-3d-reconstruction -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/trending-skills --path skills/lingbot-map-3d-reconstruction
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/lingbot-map-3d-reconstruction/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill lingbot-map-3d-reconstruction -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/lingbot-map-3d-reconstruction/SKILL.md

## When to use it
- build a point cloud from a folder of photos
- recover camera poses from a video file
- strip sky pixels from outdoor frames
- reconstruct a sequence longer than 3000 frames
- inspect the result in an interactive 3D viewer

## Example prompts
- reconstruct the 3D scene from example/church with lingbot-map
- run demo.py on video.mp4 at fps 10 with sky masking
- switch to windowed mode for a long sequence, window_size 64

## Similar
- [computer-vision-opencv](https://affpapa.org/en/nevibecode/skills/computer-vision-opencv.md) — skill · 3800 installs
- [senior-computer-vision](https://affpapa.org/en/nevibecode/skills/senior-computer-vision.md) — skill · 1152 installs
- [object-separation](https://affpapa.org/en/nevibecode/skills/object-separation.md) — skill · 1100 installs
- [segment-anything-model](https://affpapa.org/en/nevibecode/skills/segment-anything-model.md) — skill · 985 installs
- [Computer Vision](https://affpapa.org/en/nevibecode/skills/computer-vision.md) — skill · 499 installs
- [spark-training-gotchas](https://affpapa.org/en/nevibecode/skills/spark-training-gotchas.md) — skill · 2500 installs

From the same set: [reason-machines/trending-skills](https://affpapa.org/en/nevibecode/by/reason-machines/trending-skills.md) — 49 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md