PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction

arXiv:2310.07449v3 Announce Type: replace
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 …

abstract accuracy art arxiv challenges cs.cv nerf noise optimisation residual state surface type world