5,337
edits
Visual Learning and Recognition: Difference between revisions
Visual Learning and Recognition (view source)
Revision as of 18:01, 19 November 2020
, 19 November 2020→Objects + 3D
| Line 1,049: | Line 1,049: | ||
Shape carving: | Shape carving: | ||
* Assume everything is cubeoids and remove cubes. | * Assume everything is cubeoids and remove cubes. | ||
Without segmentation masks: | |||
* Train autoencoder for 3D voxels shape | |||
* Have encoder for rendered chairs. | |||
* At test time, images go to encoder for rendered and out the decoder for 3D voxels. | |||
==Will be on the exam== | ==Will be on the exam== | ||