What and Where: 3D Object Recognition with Accurate Pose

By Iryna Gordon, David G. Lowe. 2006

185 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

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

Citations in the corpus

Domain randomization for transferring deep neural networks from simulation to the real world (2017, methodology): “, Scale-Invariant Feature Transform [SIFT] features [14] or color co-occurrence histograms [12]) are matched with the 3D models (or features from the 3D models).”
HERB: a home exploring robotic butler (2010, methodology): “6.1 Related work Reliable object recognition, pose estimation and tracking are critical tasks in robotic manipulation (Taylor and Kleeman 2003; Ekvall et al. 2005; Zickler and Veloso 2006; Mittrapiyanuruk et al. 2004) and augmented reality applications (Vacchetti et al. 2004; Gordon and Lowe 2006).”
Object recognition and full pose registration from a single image for robotic manipulation (2009, methodology): “Gordon and Lowe [1] present the algorithm on which this paper is based, providing a method for accurate camera tracking using learned models of a scene and SIFT features, but no quantitative localization/orientation results are shown.”
Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image (2016, background): “For instances with sufficient texture, accurate pose estimation from RGB images has been shown by matching sparse features [17, 5, 23].”
Learning Category-Specific Deformable 3D Models for Object Reconstruction (2017, background): “Index Terms—Object reconstruction, 3D shape modeling, viewpoint estimation, scene understanding Ç”
From structure-from-motion point clouds to fast location recognition (2009, methodology): “In particular, our approach is similar to that of Gordon and Lowe [6], also utilizing structure from motion point clouds for pose estimation.”
The MOPED framework: Object recognition and pose estimation for manipulation (2011, methodology): “In this section, we formalize these inputs and outputs and introduce the terminology we use throughout the paper.”
Global Hypothesis Generation for 6D Object Pose Estimation (2016, background): “Sparse feature based methods ([8, 20]) have shown good results for accurate pose estimation.”
Voting-based pose estimation for robotic assembly using a 3D sensor (2012, methodology): “In order to handle these challenges, several invariant feature descriptors [1], [2] were used to ﬁnd the correspondences between an input image and a database of images, where the keypoints are matched with the 3D coordinates and stored ofﬂine [3], [4].”
A textured object recognition pipeline for color and depth image data (2012, methodology): “Gordon and Lowe [5] use SIFT features and structure from motion to register a camera pose against a known object model.”