Alakh Aggarwal

Alakh Aggarwal

Ph.D. Candidate
Department of Computer Science
The University of Texas at Dallas
alakh.aggarwal@utdallas.edu

Deep Learning based 3D Human Body Reconstruction

less than 1 minute read

Published:

This post mainly covers following works in brief:

  1. SMPL
  2. videoavatars
  3. Octopus
  4. DeepHuman

SMPL (Skinned Multi-Person Linear Model)

Trained parameters of an SMPL default body are as follows:

  • T ==> Mesh Vertices
  • W ==> Blending Weights
  • S ==> Shape Displacement Vectors
  • P ==> Pose Displacement Vectors
  • J ==> Joint Transformation Matrix

Given two parameters, $\theta$ for pose of human body and $\beta$ for shape of a subject, default human body is transformed to subject’s geometric characteristics and a particular pose as encoded by $\theta$

You May Also Enjoy

PhySG in equations

3 minute read

Published:

The rendering equation for PhySG, along a view-direction $o$ from camera, is defined as follows: \(R(o) = \int_{S^2} L(i) \rho_o(i) max(0, i.n) di\)

Spherical Gaussians

1 minute read

Published:

A spherical Gaussian is a function defined on the surface of a sphere. It is defined as follows:

Why do I need efficiency when I have a great GPU?

4 minute read

Published:

I got the idea of this blog post when a friend of mine shared an answer on Quora. In this answer, Miguel Oliveira explains how the Machine Learning algorithm performed effectively, that is, took less time on increasing training batch size just because of changing to a more efficient data structure for the problem. This concept is usually overlooked by many people in the industries, making them wondering if they should actually care about efficient algrithms.