A category-level 3-D object dataset: Putting the Kinect to work

By Allison Janoch, Sergey Karayev, Yangqing Jia, Jonathan T. Barron, Mario Fritz, Kate Saenko, Trevor Darrell. 2011

477 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Evaluation & Benchmarks, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

In 3D Vision & Pose

Citations in the corpus

Cross Modal Distillation for Supervision Transfer (2015, background): “ase of depth images. While the largest labeled RGB dataset, ImageNet [6] consists of over a million labeled images, the size of most existing labeled depth datasets is of the order of a few thousands [42,46,26]. At the same time there are a large number of unlabeled RGB and depth image pairs. Our te”
Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling (2018, neutral): “With depth sensors like Kinect [24, 27], the community has built various RGB-D or depth-only datasets of objects and scenes.”
SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels (2013, methodology): “Object context We note that our general framework can also be used to model contextual object relationships.”
A Large Dataset of Object Scans (2016, background): “The B3DO dataset [2] contains 849 RGB-D images of objects in their natural environments.”
Indoor Semantic Segmentation using depth information (2013, background): “Most approaches have focused on object recognition [1, 14] or point cloud semantic labeling [2], ﬁnding their applications in robotics or games [6].”
3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey (2014, background): “13 B3DO [54] Depth Image Kinect 50 850 o, c Available”
Generative Image Modeling Using Style and Structure Adversarial Networks (2016, methodology): “We perform the experiments on scene classification on SUN RGB-D dataset [61,62,63,14] as well as object detection on NYUv2 dataset.”
Superpixels: An evaluation of the state-of-the-art (2016, unknown): “Details can be found in Appendix C.1.”
Semantic Segmentation With Context Encoding and Multi-Path Decoding (2020, background): “It has 10335 indoor images which are from SUN3D [74], NYUDv2 [65], Berkeley B3DO [34] and the newly captured images.”
3D Object Detection with Multiple Kinects (2012, background): “Another dataset of 75 scenes with over 50 classes was recently proposed [10].”
SnapNet: 3D point cloud semantic labeling with 2D deep segmentation networks (2017, methodology): “We use the SUN RGB-D dataset [41] made of previous smaller RGBD datasets [42, 43, 44].”