Accurately estimating a size and a pose of a real world box in a cluttered environment is a common problem in logistics automation, yet there is no well accepted solution that performs well under different scenarios. Problem statement: Given a point cloud (i.e. a set of points in 3D) belonging to a single real world…

Reflective and transparent objects pose a common issue for depth cameras. This project describes my experiments with one of the state-of-the-art depth estimation/completion solutions. Given an RGB-D image (fig 1), use deep convolutional networks followed by a global optimization algorithm to predict the missing and erroneous depth information. Start by using only the color image…

Designed and developed a custom end-to-end model training platform for real-time instance segmentation and object detection tasks that featured: Featured are predictions on synthetic data generated by DALL-E. The model was not trained on such images, so the examples illustrate model’s generalizability to images, styles it has not seen before. As part of this work,…

When working on training any deep learning model whether it is a custom architecture or pre-trained network, it is key to obtain a detailed evaluation of the model’s performance. In scenarios, where model’s performance is below one’s expectations, I believe, it is important to understand the underlying reason to achieve significant improvements. From my personal…

Designed and developed custom deep learning architectures for semantic segmentation and classification tasks. Inspection of Car Seats Detection of Wrinkles