A large-scale hierarchical multi-view RGB-D object dataset

By Kevin Lai, Liefeng Bo, Xiaofeng Ren, Dieter Fox. 2011

1,545 citations recorded by the source corpus.

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

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

Citations in the corpus

Coupled Generative Adversarial Networks (2016, methodology): “Color and Depth Images: We used the RGBD dataset [15] and the NYU dataset [16] for learning joint distribution of color and depth images.”
Learning Rich Features from RGB-D Images for Object Detection and Segmentation (2014, background): “Object detection in RGB-D images [20,22,25,35,38], in contrast, focusses on instances, but the typical output is a bounding box.”
RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, background): “1 RGB-D object dataset University of Washington and Intel Labs Settle released this large-scale RGB-D object dataset on June 20, 2011 [52].”
Learning human activities and object affordances from RGB-D videos (2012, methodology): “For training we used the RGB-D object dataset by Lai et al. (2011a) and built a one-vs-all SVM classifier using the local features for each object class in order to obtain the probability estimates of each object class.”
Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling (2018, background): “Among those, many object datasets are designed for benchmarking robot manipulation [6, 23, 33, 51].”
Deep learning for detecting robotic grasps (2013, background): “Object detection and recognition has been a major focus in research on RGB-D data (Collet Romea et al., 2011; Lai et al., 2011; Cadena and Kosecka, 2013).”
The Curious Robot: Learning Visual Representations via Physical Interactions (2016, methodology): “We further evaluate classification on the UW RGBD dataset [42], and the Caltech-256 dataset.”
SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels (2013, background): “(a) RGB-D Object dataset [13]: multiple views of a small object; (b) Berkeley 3-D Object [11]: one view of a scene; (c) NYU Depth [20]: one corner of a room; (d) Ours: a full apartment including bedroom, living room, kitchen, and bathroom.”
Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection (2017, methodology): “As in Section 5, we use backgrounds from the UW Scenes Dataset [24] We generate a synthetic dataset with approximately 6000 images using all modes of data augmentation from Section 5.”
Real-time grasp detection using convolutional neural networks (2014, background): “Robotic systems increasingly leverage RGB-D sensors and data for tasks like object recognition [8], detection [9] [10], and mapping [11] [12].”
A Deeper Look at Dataset Bias (2015, background): “…95 classes of Caltech256 [19] and Bing [40], 89 classes of SUN [42], 35 classes of Caltech101 [11], 17 classes of Of ﬁ ce [36], 18 classes of RGB-D [27], 16 classes of Animals with At-tributes (AwA) [28] and Pascal VOC07 [9], 13 classes of MSRCORID [31], 7 classes of ETH80 [29], and 4 classes of…”
Image Segmentation Using Deep Learning: A Survey (2020, methodology): “5D datasets is UW RGB-D Object Dataset [171], which contains 300 common household objects recorded using a Kinect-style sensor.”
Incremental robot learning of new objects with fixed update time (2016, methodology): “RGB-D Washington [33] is a visual object recognition dataset comprising 300 objects belonging to 51 categories, acquired by recording image sequences of each object while rotating on a turntable.”
View-GCN: View-Based Graph Convolutional Network for 3D Shape Analysis (2020, positive): “It also outperforms the current state-of-the-art methods on real multi-view dataset RGBD [31].”
SHOT: Unique signatures of histograms for surface and texture description (2014, methodology): “[50], SHOT outperforms Spin Images and dense SIFT for the task of object category recognition on the RGB-D Object dataset [51].”