Neural Refinement for Absolute Pose Regression with Feature Synthesis

Shuai Chen, Yash Bhalgat, Xinghui Li, Jia-Wang Bian, Kejie Li, Zirui Wang, Victor Adrian Prisacariu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 20987-20996

Absolute Pose Regression (APR) methods use deep neural networks to directly regress camera poses from RGB images. However the predominant APR architectures only rely on 2D operations during inference resulting in limited accuracy of pose estimation due to the lack of 3D geometry constraints or priors. In this work we propose a test-time refinement pipeline that leverages implicit geometric constraints using a robust feature field to enhance the ability of APR methods to use 3D information during inference. We also introduce a novel Neural Feature Synthesizer (NeFeS) model which encodes 3D geometric features during training and directly renders dense novel view features at test time to refine APR methods. To enhance the robustness of our model we introduce a feature fusion module and a progressive training strategy. Our proposed method achieves state-of-the-art single-image APR accuracy on indoor and outdoor datasets. Code will be released at https://github.com/ActiveVisionLab/NeFeS.