Depth-Encoded Hough Voting for Joint Object Detection and Shape Recovery

By Min Sun, Gary R. Bradski, Bing Xu, Silvio Savarese. 2010

172 citations recorded by the source corpus.

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

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 Geology

Citations in the corpus

RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, methodology): “Compared to other Kinect object datasets, the images of B3DO are taken in “the wild” [35, 91] places by an automatic turntable setting.”
Depth-Aware Video Frame Interpolation (2019, background): “, image segmentation [41] and object detection [35].”
Recovering 6D Object Pose and Predicting Next-Best-View in the Crowd (2015, background): “5D patches that cover the same area of the object regardless of the object distance from the camera, similar to [29].”
Detailed 3D Representations for Object Recognition and Modeling (2013, background): “The implicit shape model [29] is augmented in [54] with the relative depth between codebook entries obtained from a structured light system.”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Gradient Response Maps for Real-time Detection of Texture-less Objects (methodology): “Besides pedestrian detection, there has been an approach to object classification, pose estimation and reconstruction introduced by [30].”
Learning 6D Object Pose Estimation Using 3D Object Coordinates (2014, methodology): “In [27,5], Hough voting was used for object detection, and was shown able to predict coarse object poses.”
Global Hypothesis Generation for 6D Object Pose Estimation (2016, methodology): “[7, 26] used a Hough-voting-scheme for 2D object detection and coarse pose estimation.”
Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes (2012, unknown): “In recent years, a number of methods that rely on RGBD sensors have been introduced—among them [22] which is subject to object classification, pose estimation and reconstruction.”
PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation (2019, methodology): “These approach utilize Hough voting scheme [27, 43, 12] to vote for final results with per-pixel prediction.”
Deep Hough Voting for 3D Object Detection in Point Clouds (2019, methodology): “Examples of using Hough voting include the seminal work of [22] which introduced the implicit shape model, planes extraction from 3D point clouds [3], and 6D pose estimation [42] to name a few.”
A category-level 3-D object dataset: Putting the Kinect to work (2011, methodology): “3D table top object dataset [23]: This dataset from University of Michigan covers 3 categories (mouse, mug, stapler) and provides 200 test images with cluttered backgrounds.”
FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation (2021, unknown): “Instead, dense correspondence approaches [36, 59, 14, 2, 41, 28, 12, 34, 66, 6, 6, 21, 4] find the correspondence between image pixels and mesh vertexes and recover poses within Perspective-nPoint (PnP) manners.”
PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation (2018, methodology): “In these methods, every pixel or patch produces a prediction for the desired output, and then casts a vote for the final result in a generalized Hough voting scheme [22, 34, 11].”
Enriching object detection with 2D-3D registration and continuous viewpoint estimation (2015, background): “Several attempts have been made to extend existing detectors to estimate viewpoint along with object class detections , including the implicit shape model [25], the constellation model [24], and the deformable part model [5] [8] [28] [18] [6] [11].”