Cooperative computation of stereo disparity.

By D. Marr, Tomaso A. Poggio. 1976

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

Learning a Multi-View Stereo Machine (2017, background): “Early works focused on the problem of extracting a disparity map from a binocular image pair [36].”
A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information (1993, methodology): “This scheme is somewhat analogous to the way constraints are imposed in the Marr/Poggio stereo algorithm (Marr and Poggio, 1976).”
NEUROECONOMICS: A CRITICAL RECONSIDERATION (2008, background): “Marr and Poggio (1976) was the first paper to propose this framework.”
Localist Attractor Networks (2001, background): “Attractor networks have a long history in neural network research, from relaxation models in vision (Marr & Poggio, 1976; Hummel & Zucker, 1983), to the early work of Hopeld (1982, 1984), to the stochastic Boltzmann machine (Ackley, Hinton, & Sejnowski, 1985; Movellan & McClelland, 1993), to…”
The status of the minimum principle in the theoretical analysis of visual perception. (1985, background): “ Marr and Poggio (1976) , drawing on Julesz (1971, 1974), developed a variant of the directive process models previously discussed.”
A probabilistic framework for space carving (2001, background): “[ 10 , 7, 15]) attempted to solve the 2-D disparity field which described the relationship between two images.”
The Visual System's Internal Model of the World (2015, background): “O’ Reilly et al.’s Leabra cognitive architecture [17] may be the most powerful instantiation of this class of models for recurrent processing in object recognition.”
Gradient calculations for dynamic recurrent neural networks: a survey (1995, background): “First, recurrent networks are capable of settling to a solution that satis es many constraints [1], as in a vision system which relaxes to an interpretation of an image which maximally satis es a complex set of con icting constraints [2], [3], [4], [5], [6], a system which relaxes to nd a posture fo”
Metacognition in Psychology (2019, background): “All and all, metacognition in the neurosciences focuses on the algorithmic and implementational level of explaining behavior (Marr & Poggio, 1976).”
RECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES (1978, methodology): “This position has been strongly advocated for some time by Horn [18-20] and Marr [ 26-29 ] at MIT.”
Analogical Mapping by Constraint Satisfaction (1989, methodology): “ACME: A COOPERATIVE ALGORITHM FOR MAPPING The algorithm for evaluating mappings is suggested by Marr and Poggio’s (1976) treatment of stereoscopic matching, which was based upon a cooperative algorithm, ‘ ‘ .”
Symmetric stereo matching for occlusion handling (2005, background): “On the other hand, the uniqueness constraint [15] enforces a one-to-one mapping between pixels in two images.”
Hierarchical Neural Architecture Search for Deep Stereo Matching (2020, background): “Being a classic vision problem, stereo matching has been extensively studied for almost half a century [1].”
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms (2001, methodology): “In between these two broad classes are certain iterative algorithms that do not explicitly state a global function that is to be minimized, but whose behavior mimics closely that of iterative optimization algorithms [46, 63, 83].”