Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations

Ahmadyan, Adel; Zhang, Liangkai; Wei, Jianing; Ablavatski, Artsiom; Grundmann, Matthias

doi:10.48550/arxiv.2012.09988

Cited by 5 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multi-View Cars [24] and BigBIRD [49] are real-world object-focused multi-view datasets but have limited numbers of instances and categories. The Object Scans dataset [6] and Objectron [1] are both video datasets that have the camera operator walk around various objects, but are similarly limited in the number of categories represented in the dataset. CO3D [46] also offers videos of common objects from 50 different categories, however they do not provide full 3D mesh reconstructions.…”

Section: Related Workmentioning

confidence: 99%

ABO: Dataset and Benchmarks for Real-World 3D Object Understanding

Collins¹,

Goel²,

Deng³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

ABO: Dataset and Benchmarks for Real-World 3D Object Understanding

Collins¹,

Goel²,

Deng³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The former lacks scene level labels and the latter lacks oriented 3D bounding box labels. More recent datasets such as [36] provide a variety of objects with 3D labels but do not provide depth sensor data. ARKitScenes provides the largest set of 3D oriented bounding boxes for a set of 17 room-defining object categories that addresses the gaps of previous indoor datasets.…”

Section: Related Workmentioning

confidence: 99%

ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data

Baruch¹,

Chen²,

Dehghan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Scene understanding is an active research area. Commercial depth sensors, such as Kinect, have enabled the release of several RGB-D datasets over the past few years which spawned novel methods in 3D scene understanding. More recently with the launch of the LiDAR sensor in Apple's iPads and iPhones, high quality RGB-D data is accessible to millions of people on a device they commonly use. This opens a whole new era in scene understanding for the Computer Vision community as well as app developers. The fundamental research in scene understanding together with the advances in machine learning can now impact people's everyday experiences. However, transforming these scene understanding methods to real-world experiences requires additional innovation and development. In this paper we introduce ARKitScenes. It is not only the first RGB-D dataset that is captured with a now widely available depth sensor, but to our best knowledge, it also is the largest indoor scene understanding data released. In addition to the raw and processed data from the mobile device, ARKitScenes includes high resolution depth maps captured using a stationary laser scanner, as well as manually labeled 3D oriented bounding boxes for a large taxonomy of furniture. We further analyze the usefulness of the data for two downstream tasks: 3D object detection and color-guided depth upsampling. We demonstrate that our dataset can help push the boundaries of existing state-of-the-art methods and it introduces new challenges that better represent real-world scenarios. * Equal contribution, alphabetical order.

show abstract

“…Objectron [29] dataset is a collection of short objectcentric video clips, accompanied by AR session metadata, including 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 views.…”

Section: Dataset For Category Level Object Pose Detection and Trackingmentioning

confidence: 99%

“…Then, the up-to-scale 9Dof object bounding box is recovered by solving the EPnP [43] problem. Lately, Ahmadyan et al [29] release the Objectron dataset they used and introduce MobilePose v2, a two-stage category-level 6D pose detection pipeline built upon MobilePose. In MobilePose v2, SSD [36] is first used to detect 2D object patches in the image.…”

Section: Category Level Monocular 6d Pose Detectionmentioning

confidence: 99%

Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview

Fan¹,

Zhu²,

He³

et al. 2021

Preprint

View full text Add to dashboard Cite

Object pose detection and tracking has recently attracted increasing attention due to its wide applications in many areas, such as autonomous driving, robotics, and augmented reality. Among methods for object pose detection and tracking, deep learning is the most promising one that has shown better performance than others. However, there is lack of survey study about latest development of deep learning based methods. Therefore, this paper presents a comprehensive review of recent progress in object pose detection and tracking that belongs to the deep learning technical route. To achieve a more thorough introduction, the scope of this paper is limited to methods taking monocular RGB/RGBD data as input, covering three kinds of major tasks: instance-level monocular object pose detection, category-level monocular object pose detection, and monocular object pose tracking. In our work, metrics, datasets, and methods about both detection and tracking are presented in detail. Comparative results of current state-of-the-art methods on several publicly available datasets are also presented, together with insightful observations and inspiring future research directions.

show abstract

Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations

Cited by 5 publications

References 19 publications

ABO: Dataset and Benchmarks for Real-World 3D Object Understanding

ABO: Dataset and Benchmarks for Real-World 3D Object Understanding

ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data

Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview

Contact Info

Product

Resources

About