Trained 3D Models for CNN based Object Recognition

Trained 3D Models for CNN based Object Recognition
Kripasindhu Sarkar, Kiran Varanasi, Didier Stricker
Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017) International Conference on Computer Vision Theory and Applications (VISAPP-17)

Abstract:

We present a method for 3D object recognition in 2D images which uses 3D models as the only source of the training data. Our method is particularly useful when a 3D CAD object or a scan needs to be identified in a catalogue form a given query image; where we significantly cut down the overhead of manual labeling. We take virtual snapshots of the available 3D models by a computer graphics pipeline and fine-tune existing pretrained CNN models for our object categories. Experiments show that our method performs better than the existing local-feature based recognition system in terms of recognition recall.

Keywords:

Object Recognition, Fine-tuning CNNs, Domain Fusion, Training on 3D Data, Graphics Assisted CNN.