Bilkent University
Department of Computer Engineering

---

CS 590/690 SEMİNAR

 

Refining 3D Human Texture Estimation from a Single Image

 

Said Fahri Altındiş,

Master Student
(Supervisor: Asst. Prof.Ayşegül Dündar )
Computer Engineering Department
Bilkent University

Abstract: Estimating 3D human texture from a single image is an essential task in graphics and vision. It requires learning a mapping function from input images of humans with diverse poses into the parametric (uv) space and reasonably hallucinating invisible parts. To achieve a high-quality 3D human texture estimation, we propose a framework that adaptively samples the input by a deformable convolution where offsets are learned via a deep neural network. Both offsets and the deformable convolution are deeply supervised. I will be comparing our method against the state-of-the-art approaches and display the results.

 

DATE: 5 December, Monday @ 15:30 Place: EA 502