We present an efficient method for learning part-based object class models from unsegmented images represented as sets of salient features. A model includes parts' appearance...
Abstract. Shape features applied to object recognition has been actively studied since the beginning of the field in 1950s and remain a viable alternative to appearance based metho...
We propose a novel probabilistic framework for learning
visual models of 3D object categories by combining appearance
information and geometric constraints. Objects are
represen...
Recent work in object categorization often uses local image descriptors such as SIFT to learn and detect object categories. Such descriptors explicitly code local appearance and h...
We propose a novel framework for 3D reassembly, the task of assembling a solid object from its broken pieces. The primary challenge in this under-explored problem is to robustly e...
Devi Parikh, Rahul Sukthankar, Tsuhan Chen, Mei Ch...