We report four experiments that investigated the representation of novel three-dimensional (3D) objects by the human visual system. In the first experiment, canonical views were demonstrated for novel objects seen equally often from all test viewpoints. The next two experiments showed that the canonical views persisted under repeated testing, and in the presence of a variety of depth cues, including binocular stereo. The fourth experiment probed the ability of subjects to generalize recognition to unfamiliar views of objects previously seen at a limited range of attitudes. Both mono and stereo conditions yielded the same increase in the error rate with misorientation relative to the training attitude. Taken together, these results support the notion that 3D objects are represented by multiple specific views, possibly augmented by partial viewer-centered 3D information.
Bibliographical noteFunding Information:
Acknowledgements-We are grateful to D. Weinshali for useful discussions and to Z. Liu and E. Sklar for assistancei n testing subject\. We appreciate comments by E. Hildrcth, S. Palmer, ‘I’ Poggio. P. Quinlan, S. Ullman, and J. Wolfe on earlier versions of this paper. This report describes research done within the Center for Biologica Information Processing in the Department of Brain and Cognitive Sciences at MIT. Support for this research was provided hy a grant from ONR, Cognitive and Neural Sciences Division. and by the Sloan Foundation. SE was supported by a Chaim Weizmann Postdoctoral Fellowship from the Weizmann Institute of Science.
- 3D object recognition Canonical views Novel views Stereo
ASJC Scopus subject areas
- Sensory Systems