2.5D sketch
E899003
2.5D sketch is a concept in David Marr’s theory of vision describing an intermediate visual representation that encodes surfaces, depth, and orientation from the viewer’s perspective before full 3D object recognition.
All labels observed (1)
| Label | Occurrences |
|---|---|
| 2.5D sketch canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T11002775 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 2.5D sketch Context triple: [David Marr, notableConcept, 2.5D sketch]
-
A.
3D
3D, also known as Robert Del Naja, is a British artist, musician, and founding member of the trip-hop group Massive Attack.
-
B.
3D
3D is the fourth studio album by American R&B group TLC, released in 2002 and noted for its blend of contemporary R&B and pop as well as its poignant context following the death of member Lisa "Left Eye" Lopes.
-
C.
Sketchbook
"Sketchbook" is an R&B EP by American singer Fantasia Barrino that showcases her soulful vocals and contemporary sound.
-
D.
Sketchpad
Sketchpad is a pioneering early computer graphics program, created by Ivan Sutherland in the 1960s, that introduced fundamental concepts of interactive graphical user interfaces and computer-aided design.
-
E.
The Architect Sketch
The Architect Sketch is a famous Monty Python comedy sketch in which an increasingly unhinged architect presents a disastrously overengineered and lethal building design to a pair of bewildered clients.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 2.5D sketch Target entity description: 2.5D sketch is a concept in David Marr’s theory of vision describing an intermediate visual representation that encodes surfaces, depth, and orientation from the viewer’s perspective before full 3D object recognition.
-
A.
3D
3D, also known as Robert Del Naja, is a British artist, musician, and founding member of the trip-hop group Massive Attack.
-
B.
3D
3D is the fourth studio album by American R&B group TLC, released in 2002 and noted for its blend of contemporary R&B and pop as well as its poignant context following the death of member Lisa "Left Eye" Lopes.
-
C.
Sketchbook
"Sketchbook" is an R&B EP by American singer Fantasia Barrino that showcases her soulful vocals and contemporary sound.
-
D.
Sketchpad
Sketchpad is a pioneering early computer graphics program, created by Ivan Sutherland in the 1960s, that introduced fundamental concepts of interactive graphical user interfaces and computer-aided design.
-
E.
The Architect Sketch
The Architect Sketch is a famous Monty Python comedy sketch in which an increasingly unhinged architect presents a disastrously overengineered and lethal building design to a pair of bewildered clients.
- F. None of above. chosen
Statements (47)
| Predicate | Object |
|---|---|
| instanceOf |
concept in vision science
ⓘ
intermediate representation ⓘ theoretical concept ⓘ visual representation ⓘ |
| assumes | viewer has a specific vantage point ⓘ |
| captures | visible parts of objects ⓘ |
| coordinateFrame | viewer-centered ⓘ |
| describedIn | Vision: A Computational Investigation into the Human Representation and Processing of Visual Information NERFINISHED ⓘ |
| describes | intermediate stage of visual processing ⓘ |
| developedBy | David Marr NERFINISHED ⓘ |
| distinguishedFrom |
2D image
ⓘ
full 3D model ⓘ |
| doesNotFullySpecify | object-centered shape ⓘ |
| encodes |
discontinuities in depth
ⓘ
local surface orientation ⓘ motion cues to depth ⓘ occluding contours ⓘ relative depth ⓘ shading information ⓘ texture gradients ⓘ |
| field |
cognitive science
ⓘ
computational vision ⓘ neuroscience of vision ⓘ |
| focusesOn | surfaces rather than volumetric objects ⓘ |
| goal | recover surface layout of the scene ⓘ |
| granularity | local surface patches ⓘ |
| influenced |
computational models of depth perception
ⓘ
theories of surface perception ⓘ |
| inputFrom | primal sketch ⓘ |
| levelOfProcessing | mid-level vision ⓘ |
| omits | hidden surfaces ⓘ |
| partOf | David Marr’s theory of vision NERFINISHED ⓘ |
| precedes | 3D object-centered representation ⓘ |
| publicationYearContext | 1982 ⓘ |
| relatedTo | surface-based representations in vision ⓘ |
| represents |
surface depth
ⓘ
surface orientation ⓘ viewer-centered geometry ⓘ visible surfaces ⓘ |
| role | bridge between early vision and object recognition ⓘ |
| stageIn | Marr’s three-level visual processing framework NERFINISHED ⓘ |
| supports | subsequent object recognition ⓘ |
| usesInformationFrom |
motion parallax
ⓘ
shading ⓘ stereopsis ⓘ texture ⓘ |
| viewDependence | view-dependent representation ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: 2.5D sketch Description of subject: 2.5D sketch is a concept in David Marr’s theory of vision describing an intermediate visual representation that encodes surfaces, depth, and orientation from the viewer’s perspective before full 3D object recognition.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.