Historical milestone · 1982
Computational theory of vision
Reviewed through September 18, 2026
1982 · Historical milestone
Computational theory of vision
- Era
- 1980s
- Theme
- Embodied AI & world models
- Evidence form
- Separated computational goals, algorithms/representations, and physical implementation; developed primal sketch and 2.5-D representations
- School / paradigm
- Computational neuroscience / representation
- Institution / context
- MIT
- Researchers
- David Marr
Researcher index
David Marr
Computational vision · MIT
Three levels of analysis and representations for vision
Why it still matters. Gave perception a rigorous computational and representational framework.
Representative source for this researcher — not necessarily the source of this milestone: https://mitpress.mit.edu/9780262514620/vision/ (opens in a new tab)
School of thought
Situated, embodied, and enactive AI
Matched on representative researcher.
Intelligence is inseparable from a body acting in a real environment; representation may be partial, action-oriented, or unnecessary for many behaviors.
Critique. Reactive approaches can struggle with abstraction, long-horizon planning, counterfactuals, and knowledge transfer.
Modern descendants. Embodied foundation models, VLA policies, hybrid control stacks, and spatial intelligence.
Understand
Plain-language record, transferred from the reviewed source module.
Theory or experimental setup. Created a rigorous levels-of-analysis framework and treated perception as reconstructing useful structure from images.
Result / historical claim. Primarily feedforward and task-decomposed; later work emphasized active, probabilistic, and embodied perception.
Apply
Professional implication, only where the reviewed record states one.
The checked-in record does not state a separate professional application for this entry. The topic page places it in the wider research lineage: .
Verify
Evidence status, stated limitations, and the external sources this record actually carries.
Evidence form. Separated computational goals, algorithms/representations, and physical implementation; developed primal sketch and 2.5-D representations
Limitation / debate. Vision foundation models, intermediate representations, inverse graphics, and evaluation at multiple system levels.
Source status. This milestone row does not carry a primary-source URL in the approved export, and we do not have a verified link for it in our own research. We do not guess one.
No primary-source URL is recorded for this entry in our reviewed data. Rather than manufacture a citation, we link the Implement Agentic research page that carries the record.
Reproduce
A reproduction tutorial is linked only when one exists for this exact record.
A reproduction tutorial is not yet available for this entry. The closest reviewed material is .
Cite or share
APA-like: This historical record carries a year only, and no author or publisher of record in the checked-in data. An APA reference would have to invent that metadata.
BibTeX: BibTeX requires an author and publication venue. Historical lineage entries store a narrative record and its source link, not structured authorship, so the field would be fabricated.