A ShuffleNetV2 CNN model was trained to estimate 3D object sizes using 2D images. To improve performance of the base model, the Convolutional Block Attention Module (CBAM) and image denoising techniques were integrated during training. It was found that while additional features improved base performance for obejct height and width predictions, the model still struggled to estimate object depths accurately.

A report detailing the literature review, training and testing results is linked here: A Lightweight Convolutional Neural Network model for Object Size Estimations in 2D images