// HOT3D (Hand-Object 3D Dataset) by Meta Facebook - multi-view egocentric hand and object 3D tracking for Aria/Quest smart glasses. State-of-the-art multi-view 3D hand pose, object pose, and hand-object interaction tracking. Supports visualization with 3D joint projections, meshes, and skeletal overlays on video frames.
Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.
Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.
Egocentric Hand-Object Segmentation (EgoHOS) - pixel-level hand and object segmentation in egocentric videos. Outputs fine-grained segmentation masks with hand regions highlighted. Specialized for hand-object interaction scenarios with pixel-accurate masks. Ideal for detailed interaction analysis.
Facebook Research Hand Tracking Challenge Toolkit - evaluation and visualization tools for 3D hand tracking. Supports loading HOT3D data, computing metrics (PA-MPJPE, AUC, etc.), visualizing 3D pose projections, and generating tracking evaluation reports. Essential for benchmarking hand tracking algorithms.
High-quality 3D hand pose estimation for egocentric videos from ECCV 2024 (ap229997/hands). Provides 3D joint keypoints and skeleton visualization projected to 2D. Optimized for daily egocentric activities with state-of-the-art accuracy. Outputs hand skeleton overlays on video frames.
Real-time hand detection in egocentric videos using victordibia/handtracking. Outputs bounding boxes for hands, specifically trained on EgoHands dataset. Supports video input/output with labeled hand boxes. Lightweight and fast for egocentric view applications.
| name | hot3d |
| description | HOT3D (Hand-Object 3D Dataset) by Meta Facebook - multi-view egocentric hand and object 3D tracking for Aria/Quest smart glasses. State-of-the-art multi-view 3D hand pose, object pose, and hand-object interaction tracking. Supports visualization with 3D joint projections, meshes, and skeletal overlays on video frames. |
| license | CC-BY-NC 4.0 |
| metadata | {"skill-author":"K-Dense Inc.","original-repo":"https://github.com/facebookresearch/hot3d","organization":"Meta Facebook Research","skill-category":"Computer Vision / XR","tags":["3d-tracking","multi-view","egocentric","hand-object-tracking","aria-glasses","quest","meta-xr"]} |
State-of-the-art multi-view 3D tracking system for egocentric hand-object interactions from Meta Facebook Research. Designed for Aria smart glasses and Quest VR headsets, HOT3D provides precise 3D world coordinates for hand joints, manipulated objects, and their interactions. The system includes visualization tools for rendering 3D overlays on video frames with joint projections, hand meshes, and object models.
Project page: https://facebookresearch.github.io/hot3d
Best for: Research-grade 3D tracking with multi-camera setups, high-precision applications, and XR device integration.
Use when you need:
vs alternatives:
21-keypoint 3D hand pose from multiple synchronized cameras:
6DOF object pose tracking:
Interaction analysis:
Rich visualization options:
# Clone repository
git clone https://github.com/facebookresearch/hot3d.git
cd hot3d
# Install dependencies
pip install -r requirements.txt
# Key: PyTorch3D, Open3D, vispy
# Download dataset (requires registration)
# https://facebookresearch.github.io/hot3d/dataset.html
# Run demo
python demo/visualize_tracking.py \
--sequence demo_sequence \
--output_dir ./visualizations
from hot3d import HOT3DTracker
import numpy as np
# Initialize tracker
tracker = HOT3DTracker()
tracker.load_sequence('path/to/sequence')
# Get frame data
frame_data = tracker.get_frame(frame_id=100)
# Access 3D hand pose
hand_pose_3d = frame_data['left_hand'] # 21x3 array
print(f"Wrist position: {hand_pose_3d[0]}") # [x, y, z]
# Access object pose
object_pose = frame_data['object_001']
position = object_pose['position'] # [x, y, z]
rotation = object_pose['rotation'] # 3x3 matrix
# Visualize
tracker.visualize_frame(
frame_id=100,
show_hands=True,
show_objects=True,
show_meshes=True,
save_path='output.png'
)
HOT3D dataset includes:
Access: https://facebookresearch.github.io/hot3d
Works with:
CC-BY-NC 4.0 (non-commercial only)