Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Official code for "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion"
| Date | Stars |
|---|---|
| 2026-07-24 | 496 |
| 2026-07-25 | 496 |
| 2026-07-28 | 496 |
| 2026-07-30 | 496 |
| 2026-08-06 | 496 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Official repository of HumanRF and ActorsHQ
**HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion**<br>
Mustafa Işık, Martin Rünz, Markos Georgopoulos, Taras Khakhulin, Jonathan Starck, Lourdes Agapito, Matthias Nießner
## Installation
```bash
git clone --depth=1 --recursive https://github.com/synthesiaresearch/humanrf
# Install GLM
sudo apt-get install libglm-dev
# Install required packages and Tiny CUDA NN.
pip install -r requirements.txt
pip install git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch
# Install ActorsHQ package (dataset and data loader)
cd actorshq
pip3 install .
# Install HumanRF package (method)
cd ../humanrf
pip3 install .
# Add the installation folder to the PYTHONPATH
export PYTHONPATH=$PYTHONPATH:/path/to/repo
```
## Usage
To get started quickly you can download a part of ActorsHQ and run HumanRF with the following commands:
```bash
./actorshq/dataset/download_manager.py \
actorshq_access_4x.yaml \
/tmp/actorshq \
--actor Actor01 \
--sequence Sequence1 \
--scale 4 \
--frame_start 15 \
--frame_stop 65
./humanrf/run.py \
--config example_humanrf \
--workspace /tmp/example_workspace \
--dataset.path /tmp/actorshq
```
For that you will need an access file `actorshq_access_4x.yaml`, which you can request [here](https://www.actors-hq.com/), see section "Data access and download" for more details.
## Data overview
The following datastructure is used to store the data:
```
└── Actor01
└── Sequence1
├── 1x
│ ├── calibration.csv # Camera calibration data as described below.
│ ├── light_annotations.csv # 2D annotations for light sources.
│ ├── masks # Per-frame mask for each camera.
│ │ ├── Cam001/Cam001_mask000000.png
│ │ ...
│ └── rgbs # Per-frame rgb for each camera, with background removed.
│ ├── Cam001/Cam001_rgb000000.jpg
│ ...
├── 2x
│ ...
├── 4x
│ ...
├── aabbs.csv # Per-frame axis-aligned bounding boxes of the meshes.
├── occupancy_grids # Per-frame occupancy grids.
│ ├── occupancy_grid000000.npz
│ ...
├── meshes.abc # Per-frame meshes in the Alembic format.
├── scene.blend # Blender scene file that visualizes meshes, cameras and rgb images.
└── scene.json # Scene description file that stores the number of frames.
```
## Data access and download
In order to be able to download the ActorsHQ dataset you need to request an access yaml file from [here](https://www.actors-hq.com/). This file contains the credentials to download the data from our cloud storage. Given that file you can use the `download_manager.py` program to download a subset of the data. For example, to download the first 50 frames of the first sequence of the first actor in 4x scale you can use the following command, which stores the data to `/tmp/actorshq`:
```bash
./actorshq/dataset/download_manager.py \
actorshq_access_4x.yaml \
/tmp/actorshq \
--actor Actor01 \
--sequence Sequence1 \
--scale 4 \
--frame_start 0 \
--frame_stop 50
```
## Calibration format
Calibration data is provided an `calibration.csv` files that have the following format:
```
name, w, h, rx, ry, rz, tx, ty, tz, fx, fy, px, py
Cam001, 4112, 3008, 3.14159265359, 0.0, 0.0, 1.0, 0.0, 230.0, 1.773863, 1.773863, 0.5, 0.5
...
```
Here, the rotation vector `rx, ry, rz` is in axis-angle format and focal length and principal point are normalized by image width and height.
To quickly visualize the cameras in 3D the following snippet can be used:
```python
#!/usr/bin/env python3
import numpy as np
from actorshq.dataset.camera_data import CameraData, read_calibration_csv
from matplotlib import pyplot as plt
from scipy.spatial.transform import Rotation
cameras = read_calibration_csv("/path/to/calibration.csv")
fExcerpt of 7,474 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3b5831bf18b8ea4e, topic:computer-vision, topic:nerf, topic:3d-reconstruction