COW :: Seminars ::
METU Ceng On the Web
| print-view
seminars
filter:
list | browse
id : 917
type : MSc_Thesis
dateandtime : 2019-12-16 10:40:00
duration : 90 min.
Recommended duration for PhD thesis is 90 minutes, for other seminar types, it is 60 minutes. The duration specified here is used to reserve the room.
place : A101
Please check room availability from Room Scheduling page. You must use the same room name as used in the scheduling page if you want to automatically reserve the room.
departmental : yes
title : Frankenstein3D: Human Body Reconstruction From Limited Number of Points
author : OGUZHAN TASTAN
supervisors : ASSOC.PROF.DR.YUSUF SAHILLIOGLU
Supervisors field is applicable especially for a Thesis Defense
company : Computer Engineering Dept. Middle East Technical Univ.
country : Turkey
abstract : In this thesis, we proposed a novel approach for reconstructing high-resolution 3D human body from extremely small number of 3D points which represent the parts of a human body. We leverage a data set of high-resolution 3D models of 100 humans varying from each other by physical attributes such as age, weight, size etc. We, first, divide the bodies in database into seven semantic regions (namely; head, left arm, right arm, chest, belly, left leg, right leg). Then, for each input region consisting of maximum 40 points, we search the database for the best matching shape. For the matching criteria, we use the distance between novel point-base features of input points and body parts in the database. We further combine the matched parts from different bodies into one body which result in a high resolution human body, with the help of Laplacian deformation. To evaluate our results, we pick points from each part of the ground truth bodies, then reconstruct them using our method and compare the resulting bodies with corresponding ground truth bodies. Also, our results are compared with ARAP-based results. In addition, we run our algorithm with noisy data, which produces human bodies which do not exist in our database. Our experiments show that the proposed approach reconstructs human bodies with different physical attributes from small number of points successfully.
biography :
download slides :
[ ]check this to delete slides
slidesFilename :
slidesFilename is the name of downloadable file, and will be automatically filled when you upload a new file. You may change the name also.
links :
notificationSent : final
| top
2024-03-29 18:13:15, 1711725195.070 secs
COW by: Ahmet Sacan