Description and Recognition of Curved Objects

By Ramkant Nevatia, Thomas O. Binford. 1977

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Domain randomization for transferring deep neural networks from simulation to the real world (2017, methodology): “Researchers in computer vision have used 3D models as a tool to improve performance on real images since the earliest days of the ﬁeld (e.g., [30], [24]).”
Multiview Compressive Coding for 3D Reconstruction (2023, background): “Reminiscent of generalized cylinders [41], some introduce object-specific priors via category-specific 3D templates [26,30,32], pose [43] or symmetries [73].”
DeepPose: Human Pose Estimation via Deep Neural Networks (2013, background): “The idea of representing articulated objects in general, and human pose in particular, as a graph of parts has been advocated from the early days of computer vision [16].”
3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction (2016, background): “The shape priors are typically encoded in the form of simple 3D primitives as demonstrated by early pioneering works [19,20] or learned from rich repositories of 3D CAD models [21,22,23], whereby the concept of ﬁtting 3D models to images of faces was explored to a much larger extent [24,25,26].”
Category-specific object reconstruction from a single image (2014, background): “Generalized cylinders [27] resulted in very compact descriptions for certain classes of shapes, and can be used for category level descriptions, but the fitting problem for general shapes in challenging.”
Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views (2015, methodology): “Synthesizing Images for Training Synthetic images rendered from 3D models have long been used in computer vision [25, 26, 37, 23].”
The Spatial Semantic Hierarchy (2000, methodology): “There are many reliable methods for map-building and localization within local geometric models of place neighborhoods and path segments, including occupancy grids [73,94], sonar target maps [63], and generalized cylinder models [6,74].”
Articulated Pose Estimation Using Discriminative Armlet Classifiers (2013, methodology): “The direction of representing the human body pose using stick figures was initially explored by Nevatia and Binford [18], where the body parts were modelled using generalized cylinders.”
Cascaded pose regression (2010, background): “Most commonly pose refers to geometric transformations of rigid objects [23] including the configuration of articulated objects, for example the limbs of a human body [26, 14] or vehicle layout [21].”
Sliding Shapes for 3D Object Detection in Depth Images (2014, unknown): “– Nevatia and Binford, 1977 [1].”
Learning Category-Specific Deformable 3D Models for Object Reconstruction (2017, background): “Index Terms—Object reconstruction, 3D shape modeling, viewpoint estimation, scene understanding Ç”
A Survey Of Free-Form Object Representation and Recognition Techniques (2001, background): “Generalized cylinders are defined by a space curve (representing the axis of the primitive) and a cross-section contour defined in the plane normal to the axis at and defining the boundary of the primitive along the axis[1] [ 81 ].”
Exploring Invariances in Deep Convolutional Neural Networks Using Synthetic Images (2014, methodology): “In the early days of computer vision, 3D models were used as the primary source of information to build object models (e.g., Nevatia & Binford (1977)).”
50 Years of object recognition: Directions forward (2013, background): “Binford [54] and Nevatia and Binford [38] introduced and popularized the idea of generalized-cylinder-based recognition.”
Finding Pictures of Objects in Large Collections of Images (1996, background): “The most similar ideas in computer vision are those of a body of collaborators usually seen as centered around Binford and Nevatia see, for example Nevatia and Binford, 1977; Brooks, 1981; Connell, 1987; Zerroug and Nevatia, 1994, and the work of Zisserman et al., 1995.”
From Virtual to Reality: Fast Adaptation of Virtual Object Detectors to Real Domains (2014, methodology): “The idea of using 3D models of objects as the only source of information was first introduced in the early days of computer vision, see e.g., [17].”
Poselets: Body part detectors trained using 3D human pose annotations (2009, methodology): “The formulation is similar to an SVM with the additional positivity constraint on the weights.”