Three-dimensional object recognition is viewpoint dependent

  title={Three-dimensional object recognition is viewpoint dependent},
  author={Michael J. Tarr and Pepper Williams and William G. Hayward and Isabel Gauthier},
  journal={Nature Neuroscience},
The human visual system is faced with the computationally difficult problem of achieving object constancy: identifying three-dimensional (3D) objects via two-dimensional (2D) retinal images that may be altered when the same object is seen from different viewpoints. A widely accepted class of theories holds that we first reconstruct a description of the object's 3D structure from the retinal image, then match this representation to a remembered structural description. If the same structural… 

Recognizing novel three–dimensional objects by summing signals from parts and views

  • D. FosterS. Gilson
  • Computer Science
    Proceedings of the Royal Society of London. Series B: Biological Sciences
  • 2002
Overall, visual performance proved remarkably lawful: for both long (2 s) and short (100 ms) display durations, it could be summarized by a simple, compact equation with one term representing generalized viewpoint–invariant parts–based processing of 3D object structure, including metric structure, and another term representing structure–invarial processing of 2D views.

Visual object recognition

Object recognition concerns itself with two questions: What is the form of object representation? and How do observers match object percepts to object representations? Many objects look similar and

Biologically-inspired hierarchical architectures for object recognition

This thesis aims to develop hierarchical models of the visual processing that tackle the remaining challenges of object recognition by introducing hierarchical topologies that utilise the context in which the object is found to determine the identity of the object.

Learning feature representations for an object recognition system

An object representation scheme that fits well with the view-based cortical representation of objects found in the primate inferotemporal cortex is proposed and is ideal for building humanoid cognitive architectures as it is decoupled from the recognition system.

Viewpoint Dependency in Visual Object Recognition Does Not Necessarily Imply Viewer-Centered Representation

  • M. Bar
  • Psychology
    Journal of Cognitive Neuroscience
  • 2001
It is argued that viewpoint-dependent performance is not necessarily an indication of viewer-centered representation, and it is conceivable that viewpoint dependency reflects the utilization of neural paths with different levels of sensitivity en route to the same representation, rather than the existence of viewpoint-specific representations.

Object recognition using metric shape

Matching multicomponent objects from different viewpoints: mental rotation as normalization?

  • B. WillemsJ. Wagemans
  • Psychology
    Journal of experimental psychology. Human perception and performance
  • 2001
The effects of viewpoint on performance imply that the matching of objects is viewpoint dependent and requires a process of normalization to undo the differences between the perceptual description and the stored object descriptions, but the lack of a systematic effect of the axis of rotation suggests that this normalization is best understood as not involving a 3-D transformation of stored3-D object models.



A network that learns to recognize three-dimensional objects

A scheme is developed, based on the theory of approximation of multivariate functions, that learns from a small set of perspective views a function mapping any viewpoint to a standard view, and a network equivalent to this scheme will 'recognize' the object on which it was trained from any viewpoint.

Recognition-by-components: a theory of human image understanding.

Recognition-by-components (RBC) provides a principled account of the heretofore undecided relation between the classic principles of perceptual organization and pattern recognition.

Psychophysical support for a two-dimensional view interpolation theory of object recognition.

  • H. BülthoffS. Edelman
  • Computer Science
    Proceedings of the National Academy of Sciences of the United States of America
  • 1992
The results suggest that the human visual system is better described as recognizing these objects by two-dimensional view interpolation than by alignment or other methods that rely on object-centered three-dimensional models.

Recognizing depth-rotated objects: evidence and conditions for three-dimensional viewpoint invariance.

Five experiments on the effects of changes of depth orientation on priming the naming of briefly flashed familiar objects, matching individual sample volumes (geons), and classifying unfamiliar objects all revealed immediate (i.e., not requiring practice) depth invariance.

Rotating objects to recognize them: A case study on the role of viewpoint dependency in the recognition of three-dimensional objects

  • M. Tarr
  • Business
    Psychonomic bulletin & review
  • 1995
Findings reveal a prominent role for viewpointdependent mechanisms and provide support for themultiple-views approach, in which objects are encoded as a set of view-specific representations that are matched to percepts using normalization procedures.

Recognizing novel views of three-dimensional objects.

The results indicated that the representation of the objects seen during training was quite viewpoint- specific as recognition of objects in novel orientations was relatively poor, consistent with a growing body of recent research showing that, at least under certain conditions, the visual system stores viewpoint-specific representations of objects.

Testing conditions for viewpoint invariance in object recognition.

  • W. HaywardM. Tarr
  • Psychology
    Journal of experimental psychology. Human perception and performance
  • 1997
Results suggest that the conditions proposed by I.C. Biederman and P. Gerhardstein are not generally applicable, the recognition of qualitatively distinct objects often relies on viewpoint-dependent mechanisms, and the molar features of view-based mechanisms appear to be image features rather than geons.

To What Extent Do Unique Parts Influence Recognition Across Changes in Viewpoint?

We investigated how varying the number of unique parts within an object influences recognition across changes in viewpoint The stimuli were shaded objects composed of five three-dimensional volumes

Visual cells in the temporal cortex sensitive to face view and gaze direction

Results suggest that the recognition of one type of object may proceed via the independent high level analysis of several restricted views of the object (viewer-centred descriptions).