Pairwise registration of neural fields on Neural ICP Fields

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

CC BY

Source arXiv

Computer Vision

Artificial Intelligence

Robotics

Pairwise registration of neural fields on Neural ICP Fields

nerf2nerf: Pairwise Registration of Neural Radiance Fields

We introduce a technique for pairwise registration of neural fields that extends classical optimization-based local registration (i.e.

Local registration) to operateon neural 3d scene representations trainedfrom collections of calibrated images.

We introduce the concept of a _ surface field _ that measures the likelihood of a point being on the surface of an object, and cast nerf2nerf registration as a robust optimization that iteratively seeks a rigid transformation that aligns the surface fields of the two scenes.

We evaluate the effectiveness of our technique by introducing a pre-trained neural 3d scene representation, our synthetic scenes enable quantitativeevaluations and comparisons to classical registration techniques, while our real scenes demonstrate the validity of our technique in real-world scenarios.

Authors

Lily Goli, Daniel Rebain, Sara Sabour, Animesh Garg, Andrea Tagliasacchi

◐ Recommended Follows

◐ Latest Activity