NOVA: rendering virtual worlds with humans for computer vision tasks

Kerim, Abdulrahman and Aslan, Cem and Celikcan, Ufuk and Erdem, Erkut and Erdem, Aykut (2021) NOVA: rendering virtual worlds with humans for computer vision tasks. Computer Graphics Forum, 40 (6). pp. 258-272.

Creators:
Kerim, Abdulrahman and Aslan, Cem and Celikcan, Ufuk and Erdem, Erkut and Erdem, Aykut
Description/Abstract:

Today, the cutting edge of computer vision research greatly depends on the availability of large datasets, which are critical for effectively training and testing new methods. Manually annotating visual data, however, is not only a labor-intensive process but also prone to errors. In this study, we present NOVA, a versatile framework to create realistic-looking 3D rendered worlds containing procedurally generated humans with rich pixel-level ground truth annotations. NOVA can simulate various environmental factors such as weather conditions or different times of day, and bring an exceptionally diverse set of humans to life, each having a distinct body shape, gender and age. To demonstrate NOVA's capabilities, we generate two synthetic datasets for person tracking. The first one includes 108 sequences, each with different levels of difficulty like tracking in crowded scenes or at nighttime and aims for testing the limits of current state-of-the-art trackers. A second dataset of 97 sequences with normal weather conditions is used to show how our synthetic sequences can be utilized to train and boost the performance of deep-learning based trackers. Our results indicate that the synthetic data generated by NOVA represents a good proxy of the real-world and can be exploited for computer vision tasks.

Item Type:
Article
Date:
8 May 2021
Funders:
TUBITAK-1001 Program (Grant No. 217E029), GEBIP 2018 fellowship of Turkish Academy of Sciences, BAGEP 2021 Award of the Science Academy
Identification Number:
10.1111/cgf.14271
Schools:
School of Games & Creative Technology
Research Centres:
Creative Technologies Research Centre
Depositing User:
Abdulrahman Kerim
Date Deposited:
10 Mar 2023 16:46
Last Modified:
10 Mar 2023 17:32
URI:
https://research.uca.ac.uk/id/eprint/5966

Actions (login required)

Edit View Edit View
University Staff: Request a correction | UCA Research Online Editors: Update this record