1. [Publications](/publications)
2. Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation
 
 # Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation

  ![](/sites/default/files/styles/wide/public/publications/Screenshot%202023-05-02%20at%2010.01.24.png?itok=Z_therGT)

 We present a parallelized optimization method based on fast Neural Radiance Fields (NeRF) for estimating 6-DoF target poses. Given a single observed RGB image of the target, we can predict the translation and rotation of the camera by minimizing the residual between pixels rendered from a fastNeRF model and pixels in the observed image. We integrate a momentum-based camera extrinsic optimization procedure intoInstant Neural Graphics Primitives, a recent exceptionally fastNeRF implementation. By introducing parallel Monte Carlo sampling into the pose estimation task, our method over comes local minima and improves efficiency in a more extensive search space. We also show the importance of adopting a more robust pixel-based loss function to reduce error. Experiments demonstrate that our method can achieve improved generalization and robustness on both synthetic and real-world benchmarks.



 ## Authors



Yunzhi Lin (Georgia Institute of Technology)

[Thomas Müller](/person/thomas-muller)

[Jonathan Tremblay](/person/jonathan-tremblay)

[Bowen Wen](/person/bowen-wen)

[Stephen Tyree](/person/stephen-tyree)

Alex Evans (Midjourney)

Patricio A. Vela (Georgia Institute of Technology)

[Stan Birchfield](/person/stan-birchfield)

 

 

 ## Publication Date



Monday, May 29, 2023

 

 ## Published in



[ICRA 2023](https://www.icra2023.org/)

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

[Computer Vision](/research-area/computer-vision)

[Robotics](/research-area/robotics)

 

 

 ## External Links



[Project page](https://pnerfp.github.io/)

[Video](https://www.youtube.com/watch?v=QNsiPk6zqmU)

 

 

 ## Uploaded Files



[Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation.pdf](https://d1qx31qr3h6wln.cloudfront.net/publications/Parallel%20Inversion%20of%20Neural%20Radiance%20Fields%20for%20Robust%20Pose%20Estimation.pdf "Open file in new window")5.41 MB

 

 

 ## Copyright



This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to <pubs-permissions@ieee.org>.