Vision: A Computational Investigation into the Human Representation and Processing of Visual Information¶
Marr, D. (2010). Vision: A Computational Investigation into the Human Representation and Processing of Visual Information. MIT Press.
Cited by¶
9 citations across 9 artifacts.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Black Box vs. White Box Distinction
- In computational vision, Marr's 1982 Vision: A Computational Investigation
This sourceFrames vision as a white-box problem analyzed at three levels (computational, algorithmic, implementational), specifying goals, constraints, and algorithms.
- In computational vision, Marr's 1982 Vision: A Computational Investigation
- Decomposition
- "What if this interaction were weakened?"
This sourceThe three levels of analysis — computational, algorithmic, implementational.
- "What if this interaction were weakened?"
- Feature Engineering
- Marr's levels of analysis locate representation at the algorithmic level, mediating between problem and mechanism.
This sourceIntroduces the three levels of analysis, locating representation at the algorithmic level mediating problem and mechanism, supporting the Marr's-levels anchor.
- Marr's levels of analysis locate representation at the algorithmic level, mediating between problem and mechanism.
- Gestalt Principles
- A visual stimulus typically contains thousands of discrete elements — every edge, contour, region, and color patch — and considering all pairwise relations combinatorially would exceed any reasonable processing budget, a complexity-bounding constraint Marr (1982) made central to his computational theory of vision: the visual system must use stable structural priors (organizational rules) to avoid combinatorial explosion.
This sourceEstablishes the three-level (computational/algorithmic/implementational) analysis and argues vision must use stable structural constraints/priors to render an underconstrained problem tractable. NOTE: the specific 'combinatorial explosion' wording is the prime's; it is faithful to Marr's constraint-based program (e.g., rigidity/smoothness constraints) — supporting at the level of the general claim.
- A visual stimulus typically contains thousands of discrete elements — every edge, contour, region, and color patch — and considering all pairwise relations combinatorially would exceed any reasonable processing budget, a complexity-bounding constraint Marr (1982) made central to his computational theory of vision: the visual system must use stable structural priors (organizational rules) to avoid combinatorial explosion.
- Pattern Recognition
- The stimulus encoding.
This sourceThe originating treatment of the three-level analysis — computational, algorithmic, implementational — for understanding cognitive representation; foundational for cognitive science and AI alike, and a structural template for distinguishing the what is computed from the how is it represented.)
- The stimulus encoding.
- Progressive Refinement from Core Model
- The pattern encodes a mature epistemic stance: most knowledge advances not by starting from scratch but by refining what is already known.
This sourceThe originating treatment of the three-level analysis — computational, algorithmic, implementational — for understanding cognitive representation; foundational for cognitive science and AI alike, and a structural template for distinguishing the what is computed from the how is it represented.)
- The pattern encodes a mature epistemic stance: most knowledge advances not by starting from scratch but by refining what is already known.
- Projection
- In cognition the visual system projects 3D scenes onto a 2D retinal image, and concept-formation projects rich experience onto category labels.
This sourceFrames vision as recovering scene structure from a 2D retinal projection of the 3D world.
- In cognition the visual system projects 3D scenes onto a 2D retinal image, and concept-formation projects rich experience onto category labels.
- Representation
- Cognitive science and philosophy of mind uses representation for mental representations, the symbol-grounding problem, the propositional-vs-depictive debate, the representational theory of mind, and the three-level analysis (computational / algorithmic / implementational) introduced by David Marr's Vision
This sourceThe originating treatment of the three-level analysis — computational, algorithmic, implementational — for understanding cognitive representation; foundational for cognitive science and AI alike, and a structural template for distinguishing the what is computed from the how is it represented.)
- Cognitive science and philosophy of mind uses representation for mental representations, the symbol-grounding problem, the propositional-vs-depictive debate, the representational theory of mind, and the three-level analysis (computational / algorithmic / implementational) introduced by David Marr's Vision
Domain-specific¶
- Depth Perception
- The outputs include egocentric distance from observer to object, relative or ordinal depth among objects, surface slant and curvature, and a more global three-dimensional layout.
This sourceAuthoritative computational treatment of vision as recovery of distal structure from retinal images.
- The outputs include egocentric distance from observer to object, relative or ordinal depth among objects, surface slant and curvature, and a more global three-dimensional layout.
Verification¶
Does it exist? Not checked yet. This entry carries no identifier to resolve. It was extracted from the citation as written in the article, normalized, and deduplicated against the rest of the registry.
Does it back the claim? Not recorded. Neither this nor any other of the 9 citations of this work carries a recorded support check.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:59443467e4fe · see in the full table