PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction

TL;DR

PoRF introduces an implicit pose residual field with an epipolar geometry loss to robustly refine camera poses, significantly improving neural surface reconstruction accuracy in real-world datasets.

Contribution

The paper proposes PoRF, a novel implicit pose refinement method using an MLP and epipolar geometry loss, enhancing pose accuracy for neural surface reconstruction.

Findings

Reduced rotation error by 78% on DTU dataset

Improved reconstruction F1 score from 69.18 to 75.67 on MobileBrick dataset

Outperformed ground-truth pose accuracy in some scenarios

Abstract

Neural surface reconstruction is sensitive to the camera pose noise, even if state-of-the-art pose estimators like COLMAP or ARKit are used. More importantly, existing Pose-NeRF joint optimisation methods have struggled to improve pose accuracy in challenging real-world scenarios. To overcome the challenges, we introduce the pose residual field (PoRF), a novel implicit representation that uses an MLP for regressing pose updates. This is more robust than the conventional pose parameter optimisation due to parameter sharing that leverages global information over the entire sequence. Furthermore, we propose an epipolar geometry loss to enhance the supervision that leverages the correspondences exported from COLMAP results without the extra computational overhead. Our method yields promising results. On the DTU dataset, we reduce the rotation error by 78\% for COLMAP poses, leading to the decreased reconstruction Chamfer distance from 3.48mm to 0.85mm. On the MobileBrick dataset that contains casually captured unbounded 360-degree videos, our method refines ARKit poses and improves the reconstruction F1 score from 69.18 to 75.67, outperforming that with the dataset provided ground-truth pose (75.14). These achievements demonstrate the efficacy of our approach in refining camera poses and improving the accuracy of neural surface reconstruction in real-world scenarios.