Distributed Neural Radiance Field (Di-NeRF) for Collaborative 3D Reconstruction with Relative Pose Refinement

Di-NeRF enables a group of robots to collaboratively optimize the parameters of a Neural Radiance Field (NeRF) in a distributed manner, without explicitly sharing visual data. It also jointly optimizes the relative poses of the robots, allowing for accurate 3D reconstruction with less accurate initial relative camera poses.