Investigating challenges in generalizing neural radiance fields with learned scene priors

Abstract

This thesis investigates methods to generalize neural radiance fields across several different 3DScenes. Unlike prevailing approaches that emphasize more fine grained priors on ray or sample positions - often combined with classical 3D spatial (neural) processing, this work explores the use of implicit deep scene embeddings as prior to a generalized neural radiance field for scene rendering. This work provides the theoretical groundwork for transitioning gradually from per scene retraining to a more perceiving network capable of extracting scene geometries by analyzing images and successfully building good latent representations. In practical research the framework is implemented and analyzed. Here several key issues in the conceptualization are found and analyzed, that must be addressed in training process and model redesign. Overall this thesis outlines a potential path toward scene-generalized NeRFs and highlights new issues that emerge through this shift in research focus.