Objectron
Object detection dataset
A dataset of short video clips with 3D bounding box annotations for object detection and tracking
Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes
2k stars
65 watching
263 forks
Language: Jupyter Notebook
last commit: over 2 years ago
Linked from 1 awesome list
3d3d-reconstruction3d-visionaiaugmented-realitycomputer-visiondatasetdeep-learningmachine-learningneural-networkpythonpytorchtensorflow
ly0n/awesome-robotic-toolingRelated projects:
| Repository | Description | Stars |
|---|---|---|
 google-research/kubric | Automates video data generation with realistic physics simulation and annotations for machine learning training | 2,359 |
| google-research/cad-estate | A large dataset of 3D object and room layout annotations on RGB videos, designed to test automatic scene understanding methods. | 106 |
 timzhang642/3d-machine-learning | A resource repository for 3D machine learning, providing a centralized platform for research papers, datasets, models, and courses related to 3D computer vision and machine learning. | 9,813 |
 kenshohara/3d-resnets-pytorch | PyTorch implementation of 3D ResNets for action recognition in video data | 3,920 |
 huggingface/datasets | A tool providing efficient data manipulation and loading for machine learning models | 19,349 |
 hoya012/deep_learning_object_detection | A comprehensive repository of object detection papers and datasets using deep learning techniques | 11,335 |
 wenbowen123/iros20-6d-pose-tracking | An optimization approach for long-term 6D pose tracking of objects in video sequences using synthetic data and a novel neural network architecture. | 391 |
 abhineet123/deep-learning-for-tracking-and-detection | A collection of papers, datasets, code, and resources for object tracking and detection using deep learning. | 2,441 |
 apolloscapeauto/dataset-api | A toolkit providing various datasets and utilities for autonomous driving research and development | 571 |
 pku-yuangroup/open-sora-dataset | A large video dataset collected from various open-source websites for use in computer vision and multimedia applications. | 94 |
 facebookresearch/pytorch3d | A deep learning library for 3D data processing and computer vision research using PyTorch | 8,889 |
 raulmur/orb_slam2 | A real-time SLAM system for cameras with loop detection and relocalization capabilities | 9,526 |
 ayoolaolafenwa/pixellib | A deep learning library for image segmentation and object detection using PyTorch. | 1,054 |
| facebookresearch/segment-anything | This project provides code and tools for running inference with a visual segmentation model that can generate object masks from input prompts. | 48,092 |
| facebookresearch/co-tracker | A model for tracking any point on a video using transformer-based architecture and optical flow benefits | 3,978 |