ruochenliu/3d-classification-based-on-rendered-videos

ModelNet10 classification method based on rendered videos.

3D Classification Based On Rendered Videos

Data

ModelNet10 dataset downloaded from Princeton ModelNet.

Proposed Method

Feature

• Original OFF files converted into PLY format.
• Each polygon object is rendered and taken images of from three orthogonal axes.
• Twelve images represent for each axis and are frames of one rendered video.

Network

• Plain 3D-CNN architecture with 16-filter layer stack.
• Batch normalization applied. LeakyReLU as activation function.
• Features from three axes are fed to the same network.
• Prediction is made by voting from three results.
• Model summary (link)

Experiment

• Trained for 20 epochs.
• Best test accuracy 91.6%.