NOVA: Rendering Virtual Worlds with Humans for Computer Vision Tasks

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.

Creative Image

A sample panorama displaying procedurally generated humans by the NOVA framework in a controllable, configurable environment along with their annotations. The first half is photorealistic renderings transitioning between different times of day and the latter half is demonstrating some of the pixel-level annotations NOVA generates for use in various computer vision tasks: (from left to right) instance segmentation, semantic segmentation, optical flow, surface normals and the depth data.

Please check the project webpage: NOVA Simulator


Using Synthetic Data for Person Tracking Under Adverse Weather Conditions

We introduce a novel person tracking dataset of synthetic sequences (PTAW217Synth) procedurally generated by our NOVA-Extended framework spanning the same weather conditions in varying severity to mitigate the problem of data scarcity. Our experimental results demonstrate that the performances of the state-of-the-art deep trackers under adverse weather conditions can be boosted when the available real training sequences are complemented with our synthetically generated dataset during training.

Creative Image

On the first half, sample frames from the currently-available real (top-left quarter) (MOT, NUS-PRO, OTB-100, and TC128) and synthetic (bottom-left quarter) (VIPER, PHAV, Synthia, and Virtual KITTI) visual object tracking datasets demonstrate the lack of adverse weather conditions. The second half presents sample frames from sequences spanning raining, foggy and snowy weather conditions from PTAW172Real (top-right quarter) and PTAW217Synth (bottom-right quarter) datasets that we introduce in this work.

Please check the project webpage: NOVA Adverse


Synthetic Data for Machine Learning: A Revolutionary Approach for the Future of ML With Issues, Solutions, Case Studies, and Insights

Synthetic Data for Machine Learning is a unique book to help you master synthetic data, designed to make your learning journey enjoyable. In this book, theory and good practice complement each other to provide leading-edge support!

The book helps you to overcome real data issues and improve your machine learning models' performance. It provides an overview of the fundamentals of synthetic data generation and discusses the pros and cons of each approach. It reveals the secrets of synthetic data and the best practices to leverage it better.

By the end of this book, you will master synthetic data and increase your chances of becoming a market leader. It will enable you to springboard into a more advanced, cheaper, and higher-quality data source, making you well-prepared and ahead of your peers for the next generation of machine learning!

Creative Image

The book is available on Amazon: Order the book from Amazon!