Neural Radiance Fields (NeRF) exhibit remarkable performance for Novel View
Synthesis (NVS) given a set of 2D images. However, NeRF training requires
accurate camera pose for each input view, typically obtained by
Structure-from-Motion (SfM) pipelines. Recent works have attempted to relax
this constraint, but they still often rely on decent initial poses which they
can refine. Here we aim at removing the requirement for pose initialization. We
present Incremental CONfidence (ICON), an optimization procedure for training
NeRFs from 2D video frames. ICON only assumes smooth camera motion to estimate
initial guess for poses. Further, ICON introduces ``confidence": an adaptive
measure of model quality used to dynamically reweight gradients. ICON relies on
high-confidence poses to learn NeRF, and high-confidence 3D structure (as
encoded by NeRF) to learn poses. We show that ICON, without prior pose
initialization, achieves superior performance in both CO3D and HO3D versus
methods which use SfM pose.

Neural Radiance Fields (NeRF) training is optimized using Incremental CONfidence (ICON) without prior pose initialization, leading to superior performance in CO3D and HO3D compared to methods relying on Structure-from-Motion (SfM) pose.