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.
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 ⓘ |
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.