Ashwin Nanjappa

Learn More
This paper aims to tackle the practically very challenging problem of efficient and accurate hand pose estimation from single depth images. A dedicated two-step regression forest pipeline is proposed: given an input hand depth image, step one involves mainly estimation of 3D location and in-plane rotation of the hand using a pixel-wise regression forest.(More)
We propose the first algorithm to compute the 3D Delaunay triangulation (DT) on the GPU. Our algorithm uses massively parallel point insertion followed by bilateral flipping, a powerful local operation in computational geometry. Although a flipping algorithm is very amenable to parallel processing and has been employed to construct the 2D DT and the 3D(More)
A novel algorithm is presented to compute the convex hull of a point set in &#x211D;<sup>3</sup> using the graphics processing unit (GPU). By exploiting the relationship between the Voronoi diagram and the convex hull, the algorithm derives the approximation of the convex hull from the former. The other extreme vertices of the convex hull are then found by(More)
We present a novel algorithm to compute the convex hull of a point set in R 3 using the graphics processing unit (GPU). By exploiting the relationship between the Voronoi diagram and the convex hull, we derive the answer from the former. Our algorithm only requires a few simple atomic operations and does not need explicit locking or any other concurrency(More)
We focus on the challenging problem of efficient mouse 3D pose estimation based on static images, and especially single depth images. We introduce an approach to discriminatively train the split nodes of trees in random forest to improve their performance on estimation of 3D joint positions of mouse. Our algorithm is capable of working with different types(More)
Display Operation volume Beamsplitter Depth camera (c) (b) (a) (d) 15 joints 27 DoF Figure 1: (a) Kinematic chain model (b) Demo of GHand (c) Results on poses with interlocking and occluded fingers (d) Demo of 3D-CuBE Abstract We present GHand, a GPU algorithm for markerless hand pose estimation from a single depth image obtained from a commodity depth(More)
AIMS (1) To compare the sealing ability of mineral trioxide aggregate (MTA), Biodentine, and Chitra-calcium phosphate cement (CPC) when used as root-end filling, evaluated under confocal laser scanning microscope using Rhodamine B dye. (2) To evaluate effect of ultrasonic retroprep tip and an erbium:yttrium aluminium garnet (Er:YAG) laser on the integrity(More)
  • 1