OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Humanrf

HumanRF is a Python research codebase that reconstructs neural radiance fields of people in motion, with a documented workflow using the ActorsHQ dataset.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Humanrf — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use HumanRF when you need a self-hosted research workflow for reconstructing moving people as neural radiance fields and can work with its documented Python and CUDA-related setup.

Who it is for

  • Computer-vision and graphics researchers studying human-motion reconstruction
  • Developers building research workflows or visualization tools around reconstructed human scenes

Documented uses

  • Run a documented HumanRF reconstruction workflow on an ActorsHQ data subset
  • Download selected ActorsHQ actors, sequences and frame ranges
  • Prepare ActorsHQ data for related Blender or COLMAP workflows
Before you choose

Requirements & limits

The repository is public. Downloading ActorsHQ data requires an access YAML file requested from the ActorsHQ website.

  • The setup requires Python packages, PyTorch bindings for Tiny CUDA NN, GLM and CUDA-related dependencies.
  • The documented quick-start relies on ActorsHQ data and its access credentials.
  • The repository also includes dataset utilities such as Blender and COLMAP exports, separate from the HumanRF method.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install HumanRF and its documented dependencies

Prepare the repository’s Python packages and environment for the documented HumanRF workflow.

Before you start

  • A Linux environment with the documented CUDA-related dependencies
  • Git, pip and access to install the listed packages

Steps

  1. Clone the HumanRF repository recursively.

  2. Install GLM with the documented apt package.

  3. Install the requirements and Tiny CUDA NN PyTorch bindings.

  4. Install the ActorsHQ package and HumanRF package, then add the repository installation folder to PYTHONPATH.

Expected outcome

The repository and its documented method and dataset packages are installed.

Guide limitations

  • These are setup instructions; they do not verify successful installation or provide a reconstruction result.
  • The documented run example additionally requires ActorsHQ data and an access YAML file.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
synthesiaresearch/humanrf · Official homepage title · retained in its source language
How we review sourcesSuggest a correction