Deep Learning approaches meet 3D data

Talk presentation

Interview with the speaker

During this talk, I’d be talking about how 3d data can be processed with Deep Learning models. The main focus would be on Point Clouds.

Session agenda:

1. What are 3D data and its representation
2. Overview of libraries to visualize and process
3. How to collect. Cameras. Calibration
4. The current state of the art for point cloud processing with Deep Learning models.

• classification problem. Models to use
• segmentation problem. Models to use
• datasets. Losses and training routine

5. Point clouds correspondences

• spectral methods to generate correspondences

6. Limitations.