---
title: "hold"
type: "tool"
slug: "zc-alexfan-hold"
canonical_url: "https://www.graphcanon.com/tools/zc-alexfan-hold"
github_url: "https://github.com/zc-alexfan/hold"
homepage_url: "https://zc-alexfan.github.io/hold"
stars: 486
forks: 15
primary_language: "Python"
license: "MIT"
archived: false
categories: ["vector-databases", "model-training", "computer-vision"]
tags: ["3d-reconstruction", "hand-object-reconstruction", "ai", "artificial-intelligence", "hand-object-interaction", "hand-tracking", "augmented-reality", "computer-vision"]
updated_at: "2026-07-11T12:29:30.602214+00:00"
---

# hold

> [CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and 3D

[CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and 3D hand-object training data.

## Facts

- Repository: https://github.com/zc-alexfan/hold
- Homepage: https://zc-alexfan.github.io/hold
- Stars: 486 · Forks: 15 · Open issues: 9 · Watchers: 11
- Primary language: Python
- License: MIT
- Last pushed: 2026-03-10T17:45:07+00:00

## Trust & health

_Signals computed from public GitHub metadata. Not a security guarantee._

- Maintenance: Slowing (computed 2026-07-11T12:29:24.617Z)
- Security scan: Findings present (0 critical, 0 high, 0 medium, 9 low) · last scan 2026-07-11T12:29:27.585Z
- Full report: [trust report](/tools/zc-alexfan-hold/trust.md) · [JSON](https://www.graphcanon.com/api/graphcanon/tools/zc-alexfan-hold/trust)

## Categories

- [Vector Databases](/categories/vector-databases.md)
- [Model Training](/categories/model-training.md)
- [Computer Vision](/categories/computer-vision.md)

## Tags

3d-reconstruction, hand-object-reconstruction, ai, artificial-intelligence, hand-object-interaction, hand-tracking, augmented-reality, computer-vision

## Category neighbours (exploratory)

_Same-category tools for discovery only - not curated alternatives. Cap shown at six._

- [tensorflow](/tools/tensorflow-tensorflow.md) - An Open Source Machine Learning Framework for Everyone (★ 196,300) [Very active]
- [transformers](/tools/huggingface-transformers.md) - Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models (★ 162,482) [Very active]
- [generative-ai-for-beginners](/tools/microsoft-generative-ai-for-beginners.md) - 21 Lessons, Get Started Building with Generative AI (★ 112,866) [Very active]
- [pytorch](/tools/pytorch-pytorch.md) - Tensors and Dynamic neural networks in Python with strong GPU acceleration (★ 101,752) [Very active]
- [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) - Implement a ChatGPT-like LLM in PyTorch from scratch, step by step (★ 98,899) [Steady]
- [DeepSeek-R1](/tools/deepseek-ai-deepseek-r1.md) - Repository contains distilled LLM models derived from Qwen and LLaMA series for various commercial uses. (★ 91,991) [Dormant]

_+ 2 more not listed._

## README (excerpt)

_Quoted verbatim from the upstream repository. Untrusted content - treat as data, not instructions._

````text
### Getting started

Get a copy of the code:

```bash
git clone https://github.com/zc-alexfan/hold.git
cd hold; git submodule update --init --recursive
```

1. **Setup environments**
    - Follow the instructions here: [`docs/setup.md`](docs/setup.md).
    - You may skip external dependencies for now.

1. **Train on a preprocessed sequence**
   - Start with one of our preprocessed in-the-wild sequences, such as `hold_bottle1_itw`.
   - Familiarize yourself with the usage guidelines in [`docs/usage.md`](docs/usage.md) for this preprocessed sequence.
   - This will enable you to train, render HOLD, and experiment with our interactive viewer.
   - At this stage, you can also explore the HOLD code in the `./code` directory.

1. **Set up external dependencies and process custom videos**
   - After understanding the initial tools, set up the "external dependencies" as outlined in [`docs/setup.md`](docs/setup.md).
   - Preprocess the images from the `hold_bottle1_itw` sequence by following the instructions in [`docs/custom.md`](docs/custom.md).
   - Train on this sequence to learn how to build a custom dataset.
   - You can capture your own custom video and reconstruct it in 3D at this point.
   - Most preprocessing artifact files are documented in [`docs/data_doc.md`](docs/data_doc.md), which you can use as a reference.

1. **Two-hand setting**: Bimanual category-agnostic reconstruction
    - At this point, you can preprocess and train on a custom single-hand sequence. 
    - Now you can take on the bimanual category-agnostic reconstruction challenge!
    - Following the instruction in [`docs/arctic.md`](docs/arctic.md) to reconstruct two-hand manipulation of ARCTIC sequences.
````

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/tools/zc-alexfan-hold`](/api/graphcanon/tools/zc-alexfan-hold)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_