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

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

doi:10.1109/cvpr46437.2021.00773

Cited by 110 publications

(74 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method can also be trained on real-data that consists of image pairs of the same object which vary in their viewpoints. To this end, we use the recently proposed Objectron dataset [1], and the Freiburg cars dataset [48]. For Objectron we train on the chair category, as it is present in ShapeNet and contains sufficiently diverse high-quality images in contrast to the other categories where images are blurry or there are too few videos.…”

Section: Other Dataset Resultsmentioning

confidence: 99%

“…Alternatively, coarse viewpoint estimation can be obtained without manual annotations using structure from motion algorithms on videos [48,40]. Ground truth pose annotations are challenging to acquire, and recent benchmarks still require human intervention in order to set the coordinate system for each instance and to correct automatic pose errors [1]. 3D-aware representations.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

ViewNet: Unsupervised Viewpoint Estimation from Conditional Generation

Mariotti

Aodha²,

Bilen³

2021

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Understanding the 3D world without supervision is currently a major challenge in computer vision as the annotations required to supervise deep networks for tasks in this domain are expensive to obtain on a large scale. In this paper, we address the problem of unsupervised viewpoint estimation. We formulate this as a self-supervised learning task, where image reconstruction provides the supervision needed to predict the camera viewpoint. Specifically, we make use of pairs of images of the same object at training time, from unknown viewpoints, to self-supervise training by combining the viewpoint information from one image with the appearance information from the other. We demonstrate that using a perspective spatial transformer allows efficient viewpoint learning, outperforming existing unsupervised approaches on synthetic data, and obtains competitive results on the challenging PASCAL3D+ dataset.

show abstract

Section: Other Dataset Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

ViewNet: Unsupervised Viewpoint Estimation from Conditional Generation

Mariotti

Aodha²,

Bilen³

2021

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…Datasets. We performed experiments on two datasets, Objectron [2] and the ImageNetVid and ImageNetVid-Robust datasets described in Sect. 1.1.…”

Section: Methodsmentioning

confidence: 99%

“…1.1. Objectron [2] contains short video clips of scenes with 9 classes: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes. We split it into a training and a validation set, with an equal number of videos of each class in each split.…”

Section: Methodsmentioning

confidence: 99%

Scene Uncertainty and the Wellington Posterior of Deterministic Image Classifiers

Tsuei¹,

Golatkar²,

Soatto³

2021

Preprint

View full text Add to dashboard Cite

We propose a method to estimate the uncertainty of the outcome of an image classifier on a given input datum. Deep neural networks commonly used for image classification are deterministic maps from an input image to an output class. As such, their outcome on a given datum involves no uncertainty, so we must specify what variability we are referring to when defining, measuring and interpreting "confidence." To this end, we introduce the Wellington Posterior, which is the distribution of outcomes that would have been obtained in response to data that could have been generated by the same scene that produced the given image. Since there are infinitely many scenes that could have generated the given image, the Wellington Posterior requires induction from scenes other than the one portrayed. We explore alternate methods using data augmentation, ensembling, and model linearization. Additional alternatives include generative adversarial networks, conditional prior networks, and supervised single-view reconstruction. We test these alternatives against the empirical posterior obtained by inferring the class of temporally adjacent frames in a video. These developments are only a small step towards assessing the reliability of deep network classifiers in a manner that is compatible with safety-critical applications.

show abstract

“…Objectron. Recently, Google released the Objectron dataset (Ahmadyan et al, 2021), which is composed of object centric video clips capturing nine different objects categories in indoor and outdoor scenarios. The dataset consists of 14,819 annotated video clips containing over four million annotated images.…”

Section: Indoor Datasetsmentioning

confidence: 99%

Survey and Systematization of 3D Object Detection Models and Methods

Moritz¹,

Friederich²,

Egger³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper offers a comprehensive survey of recent developments in 3D object detection covering the full pipeline from input data, over data representation and feature extraction to the actual detection modules. We include basic concepts, focus our survey on a broad spectrum of different approaches arising in the last ten years and propose a systematization which offers a practical framework to compare those approaches on the methods level.

show abstract

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

Cited by 110 publications

References 15 publications

ViewNet: Unsupervised Viewpoint Estimation from Conditional Generation

ViewNet: Unsupervised Viewpoint Estimation from Conditional Generation

Scene Uncertainty and the Wellington Posterior of Deterministic Image Classifiers

Survey and Systematization of 3D Object Detection Models and Methods

Contact Info

Product

Resources

About