K3BO: Keypoint-Based Bounding Box Optimization for Radiance Field Reconstruction from Multi-View Images
Résumé
Novel view synthesis has recently been approached with Neural radiance fields, for high quality rendering. While those methods initially addressed the whole scene with a single global function, many state-of-the-art methods decompose the scene by spatially encoding feature vectors. High speed and quality are achieved, but reconstruction stability is still fragile. This usually requires human supervision through data pre-processing, preventing a robust, fully automatic chain for volumetric reconstruction of the visual scene. We observe that stability and quality can be improved by interpreting the scene beforehand, in order to properly set its bounding box. We propose a simple and robust approach to fit the scene volume bounds based on sparse point clouds processed by a Structure From Motion (SfM) pipeline. The benefit of this method is shown over multiple scenes and two state-of-the-art radiance field reconstruction methods.