Machine Perception of Three-Dimensional Solids

By L. Roberts. 1963

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Lifting Object Detection Datasets into 3D (2015, background): “In certain cases a precise 3D model of the target object is known [22], [23] and the problem can be seen as a special case of class-based reconstruction that focuses on reconstructing a speciﬁc instance of the class.”
Category-specific object reconstruction from a single image (2014, methodology): “Other representations such as solid models [21, 48], which trace back to the early work of Roberts [36], and CAD models [32, 38], can represent a limited set of shapes but are robust to noise in lower level inputs, which are used mostly for determining viewpoint.”
Reasoning About Physical Interactions with Object-Oriented Prediction and Planning (2018, background): “Despite being a core focus of the earliest days of artiﬁcial intelligence and computer vision research (Roberts, 1963; Winston, 1970), a similar level of physical scene understanding remains elusive for machines.”
Crisp Boundary Detection Using Pointwise Mutual Information (2014, methodology): “Classical examples are the Sobel [11], Roberts [12], Prewitt [13] and Canny [14] edge detectors, which all use local derivative ﬁlters of ﬁxed scale and only a few orientations.”
Learning 3D Object Categories by Looking Around Them (2017, methodology): “A traditional approach to 3D reconstruction is to use handcrafted 3D models [29, 21], and more recently 3D CAD models [5, 43].”
Learning to Infer and Execute 3D Shape Programs (2019, background): “A few recent papers have explored the use of simple geometric primitives to describe shapes (Tulsiani et al., 2017; Zou et al., 2017; Liu et al., 2018), putting the classic idea of generalized cylinders (Roberts, 1963; Binford, 1971) or geons (Biederman, 1987) in the modern context of deep learning.”
Learning Shape Templates With Structured Implicit Functions (2019, methodology): “Primitive Fitting: Fitting of basic primitives is perhaps the oldest topic in 3D computer vision, beginning with Roberts [42] and continuing to today [2, 19, 29, 27].”
50 years of biometric research: Accomplishments, challenges, and opportunities (2016, unknown): “Coincidentally, modern computer vision5 also had its beginnings approximately 50 years ago, with Roberts’ PhD dissertation on machine vision of 3D solids (Roberts, 1963).”
Evolving large-scale neural networks for vision-based TORCS (2013, methodology): “The saturation plane is passed through Robert’s edge detector [12] and then fed into a Elman (recurrent) neural network (SRN) with 16 × 16 = 256 fully-interconnected neurons in the hidden layer, and 3 output neurons.”
Warning Concerning Copyright Restrictions (2008, methodology): “One was the work of the group at the Carnegie Institute of Technology beginning in the late fifties which led to the first list-processing system known as the Information Processing Language (see the historical notes in Newell & Simon, 1972).”
Tiramisu: A Polyhedral Compiler for Expressing Fast and Portable Code (2018, methodology): “We used the following image processing benchmarks in our evaluation: edgeDetector, a ring blur followed by Roberts edge detection [42]; cvtColor, which converts an RGB image to grayscale; conv2D, a simple 2D convolution; warpAffine, which does affine warping on an image; gaussian, which performs a g”
Learning Category-Specific Deformable 3D Models for Object Reconstruction (2017, background): “Index Terms—Object reconstruction, 3D shape modeling, viewpoint estimation, scene understanding Ç”
Description and Recognition of Curved Objects (1977, background): “Previous work in three-dimensional scene analysis has concentrated on scenes contai'ning polyhedral objects only [8, 9, 12 , 14].”
A Simple Yet Effective Baseline for 3d Human Pose Estimation (2017, background): “Top-down 3d reasoning One of the first algorithms for depth estimation took a different approach: exploiting the known 3d structure of the objects in the scene [37].”