Can I read 3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations on EtoBox?

3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations by Prabhudesai, Mihir; Lal, Shamit; Tung, Hsiao-Yu Fish; Harley, Adam W.; Potdar, Shubhankar; Fragkiadaki, Katerina is a scholarly article available to read on EtoBox.

What is 3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations about?

We propose a system that learns to detect objects and infer their 3D poses in RGB-D images. Many existing systems can identify objects and infer 3D poses, but they heavily rely on human labels and 3D annotations. The challenge here is to achieve this without relying on strong supervision signals. To address this challenge, we propose a model that maps RGB-D images to a set of 3D visual feature maps in a differentiable fully-convolutional manner, supervised by predicting views. The 3D feature maps correspond to a featurization of the 3D world scene depicted in the images. The object 3D feature representations are invariant to camera viewpoint changes or zooms, which means feature matching can identify similar objects under different camera viewpoints. We can compare the 3D feature maps of two objects by searching alignment across scales and 3D rotations, and, as a result of the operation, we can estimate pose and scale changes without the need for 3D pose annotations. We cluster object feature maps into a set of 3D prototypes that represent familiar objects in canonical scales and orientations. We then parse images by inferring the prototype identity and 3D pose for each detected ob

Author

Prabhudesai, Mihir; Lal, Shamit; Tung, Hsiao-Yu Fish; Harley, Adam W.; Potdar, Shubhankar; Fragkiadaki, Katerina

Published

2020

Language

EN