2022/03/30 by David Dadon, Ohad Fried, Dadon, David +3 · 1 citation
Computer Science · #Advanced Vision and Imaging #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Graphics (cs.GR) #Optical measurement and interference techniques
paper · pdf · doi:10.48550/arxiv.2203.16626
openalex publication_date 2022/03/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In recent years, the field of implicit neural representation has progressed significantly. Models such as neural radiance fields (NeRF), which uses relatively small neural networks, can represent high-quality scenes and achieve state-of-the-art results for novel view synthesis. Training these types of networks, however, is still computationally very expensive. We present depth distribution neural radiance field (DDNeRF), a new method that significantly increases sampling efficiency along rays during training while achieving superior results for a given sampling budget. DDNeRF achieves this by learning a more accurate representation of the density distribution along rays. More specifically, we train a coarse model to predict the internal distribution of the transparency of an input volume in addition to the volume's total density. This finer distribution then guides the sampling procedure of the fine model. This method allows us to use fewer samples during training while reducing computational resources.