https://arxiv.org/pdf/2308.10902.pdf
“…any errors in the camera position solve can dramatically reduce the quality of a reconstruction. “
“Introducing CamP — a method to precondition camera optimization for NeRFs to significantly improve quality. With CamP we’re able to create high quality reconstructions even when input poses are bad.
CamP is a general purpose trick that you can apply in many places. Apply CamP to prior SOTA NeRF models like Zip-NeRF, and you improve quality and establish a new SOTA. Applying CamP to existing camera optimization models, like SCNeRF, to improve their performance.” – Keunhong Park
(a) ARKit Poses (w/o COLMAP) (b) ARKit Poses + CamP (Ours)
