Project Name | Stars | Downloads | Repos Using This | Packages Using This | Most Recent Commit | Total Releases | Latest Release | Open Issues | License | Language |
---|---|---|---|---|---|---|---|---|---|---|
Objectron | 1,958 | a year ago | 21 | other | Jupyter Notebook | |||||
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 | ||||||||||
Jeelizweboji | 1,008 | a month ago | 2 | April 30, 2021 | apache-2.0 | JavaScript | ||||
JavaScript/WebGL real-time face tracking and expression detection library. Build your own emoticons animated in real time in the browser! SVG and THREE.js integration demos are provided. | ||||||||||
Awesome Virtual Try On | 995 | 16 days ago | 4 | |||||||
A curated list of awesome research papers, projects, code, dataset, workshops etc. related to virtual try-on. | ||||||||||
Opensse | 876 | 2 years ago | other | C++ | ||||||
Open Sketch Search Engine- 3D object retrieval based on sketch image as input | ||||||||||
Video Classification 3d Cnn Pytorch | 749 | 5 years ago | 33 | mit | Python | |||||
Video classification tools using 3D ResNet | ||||||||||
Video To Pose3d | 601 | 4 days ago | 18 | mit | Python | |||||
Convert video to 3D pose in one-key. | ||||||||||
Efficient 3dcnns | 549 | a year ago | 13 | mit | Python | |||||
PyTorch Implementation of "Resource Efficient 3D Convolutional Neural Networks", codes and pretrained models. | ||||||||||
Objectposeestimationsummary | 518 | 7 months ago | mit | Python | ||||||
Resources (papers, datasets, rendering methods) in the domain of object pose estimation. | ||||||||||
Video Classification | 498 | 3 years ago | 26 | Jupyter Notebook | ||||||
Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101 | ||||||||||
Universalviewer | 433 | 2 | 9 days ago | 5 | February 28, 2018 | 247 | other | TypeScript | ||
A community-developed open source project on a mission to help you share your 📚📜📰📽️📻🗿 with the 🌎 |
Objectron is a dataset of short object centric video clips with pose annotations.
The Objectron dataset is a collection of short, object-centric video clips, which are accompanied by AR session metadata that includes camera poses, sparse point-clouds and characterization of the planar surfaces in the surrounding environment. In each video, the camera moves around the object, capturing it from different angles. The data also contain manually annotated 3D bounding boxes for each object, which describe the object’s position, orientation, and dimensions. The dataset consists of 15K annotated video clips supplemented with over 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops
, and shoes
. In addition, to ensure geo-diversity, our dataset is collected from 10 countries across five continents. Along with the dataset, we are also sharing a 3D object detection solution for four categories of objects — shoes, chairs, mugs, and cameras. These models are trained using this dataset, and are released in MediaPipe, Google's open source framework for cross-platform customizable ML solutions for live and streaming media.
The data is stored in the objectron bucket on Google Cloud storage. Check out the Download Data notebook for a quick review of how to download/access the dataset. The following assets are available:
/videos/class/batch-i/j/video.MOV
files)/videos/class/batch-i/j/geometry.pbdata
files. They are formatted using the object.proto. See [example] on how to parse the annotation files.tf.records
of the annotated frames, in tf.example format and videos in tf.SequenceExample
format. These are used for creating the input data pipeline to your models. These files are located in /v1/records_shuffled/class/
and /v1/sequences/class/
.Raw dataset size is 1.9TB (including videos and their annotations). Total dataset size is 4.4TB (including videos, records, sequences, etc.). This repository provides the required schemas and tools to parse the dataset.
class | bike | book | bottle | camera | cereal_box | chair | cup | laptop | shoe |
---|---|---|---|---|---|---|---|---|---|
#videos | 476 | 2024 | 1928 | 815 | 1609 | 1943 | 2204 | 1473 | 2116 |
#frames | 150k | 576k | 476k | 233k | 396k | 488k | 546k | 485k | 557k |
Objectron is released under Computational Use of Data Agreement 1.0 (C-UDA-1.0). A copy of the license is available in this repository.
If you found this dataset useful, please cite our paper.
@article{objectron2021,
title={Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations},
author={Adel Ahmadyan, Liangkai Zhang, Artsiom Ablavatski, Jianing Wei, Matthias Grundmann},
journal={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
year={2021}
}
This is not an officially supported Google product. If you have any question, you can email us at [email protected] or join our mailing list at [email protected]