Abstract. Cast shadows are an informative cue to the shape of objects. They are particularly valuable for discovering object’s concavities which are not available from other cues...
Silvio Savarese, Marco Andreetto, Holly E. Rushmei...
In this paper, we present a novel approach for extracting silhouettes by using a particular pattern that we call the random pattern. The volume intersection method reconstructs th...
3D human pose recovery is considered as a fundamental step in view-invariant human action recognition. However, inferring 3D poses from a single view usually is slow due to the la...
The paper presents a novel coding technique based on approximate geometry for images taken from arbitrary recording positions around a 3-D scene. Such data structures occur in ima...
In this paper, we represent human actions as short sequences of atomic body poses. The knowledge of body pose is stored only implicitly as a set of silhouettes seen from multiple ...
Abhijit S. Ogale, Alap Karapurkar, Yiannis Aloimon...