Object discovery in 3D scenes via shape analysis

By Andrej Karpathy, Stephen D. Miller, Li Fei-Fei. 2013

208 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Environmental Engineering

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 Environmental Engineering

Citations in the corpus

Spatially Invariant Unsupervised Object Detection with Convolutional Neural Networks (2019, methodology): “Related work from computer vision includes (Cao and Fei-Fei 2007; Kim and Torralba 2009; Lee and Grauman 2009; Russell et al. 2006; Karpathy, Miller, and Fei-Fei 2013), as well as work on co-segmentation (Zhu et al. 2016) and unsupervised object recognition (Tuytelaars et al. 2010).”
RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, methodology): “The curves under the images are the accelerometer data at 50 Hz of devices attached to the knife, the mixing spoon, the small spoon, the peeler, the glass, the oil bottle, and the pepper dispenser mentioned datasets above, another 26 extra RGB-D datasets for different applications are also added int”
ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes (2017, methodology): “Our use of commodity RGB-D sensors necessitates unwarping of depth data and alignment of depth and color data.”
3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection (2016, background): “In [23], candidate objects are proposed from 3D meshes by oversegmentation and several intrinsic shape measures.”
SceneGrok (2014, methodology): “For each 3D mesh, we oversegment the geometry using a graph segmentation method [Felzenszwalb and Huttenlocher 2004] with a distance metric based on surface normals [Karpathy et al. 2013].”
Salient object detection: A survey (2014, methodology): “on [198]–[201], content-based image retrieval and image collection browsing [178], [202]–[204], image editing and manipulating [41], [176], [179], [180], visual tracking [205]–[211], object discovery [212], [213], and human-robot interaction [214], [215]. Fig.11shows example applications. 4 DATASETS”
Unsupervised discovery of object classes with a mobile robot (2014, background): “[17]) objects can be extracted from clutter directly.”
Object detection and classification from large‐scale cluttered indoor scans (2014, methodology): “A method for detecting good object candidates in indoor scenes, based on a set of indicators like repetition, has been proposed recently by Karpathy et al. [KMFF13].”
A Robust 3D-2D Interactive Tool for Scene Segmentation and Annotation (2016, unknown): “, in [45].”
Scene Understanding by Reasoning Stability and Safety (2015, background): “…many semantic labeling methods for 3D point clouds play an important role in robotics: Koppula et al. (2011); Anand et al. (2012); Wu et al. (2014), etc; in graphics: e.g., Nan et al. (2012); Shao et al. (2012) (2014); Savva et al. (2014), etc; in 3D shape recognition: Karpathy et al. (2013), etc.”
Multiview RGB-D Dataset for Object Instance Detection (2016, background): “[13] performs object discovery by ranking 3D mesh segments based on objectness scores.”
Salient Object Detection in the Deep Learning Era: An In-Depth Survey (2019, background): “Example applications in robotics, such as human-robot interaction [22], [23], and object discovery [24], [25] also beneﬁt from SOD for scene understanding.”
Affordance detection of tool parts from geometric features (2015, background): “Usually, great care must be taken to find segments that have not oversegmented or undersegmented an object of interest [16].”
MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects (2018, methodology): “Some methods have proposed to segment RGBD data based on geometric properties of surface normals [9, 13, 22, 45], mainly by assuming that objects are convex.”
Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement (2022, methodology): “Given a scene in mesh format, we first oversegment the meshes using a normal-based graph cut method [9,13].”
You-Do, I-Learn: Egocentric unsupervised discovery of objects and their modes of interaction towards video-based guidance (2015, methodology): “[24, 21, 22, 51]) of an object based on visual similarity.”
Monocular 3D Object Detection for Autonomous Driving (2016, background): “In RGB-D, [10] exploited stereo imagery to exhaustively scored 3D bounding boxes using a conditional random field with several depth-informed potentials.”
Pattern Recognition (2015, unknown): “We therefore remove outliers from our result, borrowing ideas from the stereo matching literature [19].”