Neural Adaptive Scene Tracing (NAScenT)

Abstract
Neural rendering with implicit neural networks has recently emerged as an attractive proposition for scene reconstruction, achieving excellent quality albeit at high computational cost. While the most recent generation of such methods has made progress on the rendering (inference) times, very little progress has been made on improving the reconstruction (training) times. In this work we present Neural Adaptive Scene Tracing (NAScenT ), that directly trains a hybrid explicit-implicit neural representation. NAScenT uses a hierarchical octree representation with one neural network per leaf node and combines this representation with a two-stage sampling process that concentrates ray samples where they matter most - near object surfaces. As a result, NAScenT is capable of reconstructing challenging scenes including both large, sparsely populated volumes like UAV captured outdoor environments, as well as small scenes with high geometric complexity. NAScenT outperforms existing neural rendering approaches in terms of both quality and training time.
Description

CCS Concepts: Computing methodologies --> Ray tracing; Image-based rendering

        
@inproceedings{
10.2312:vmv.20221199
, booktitle = {
Vision, Modeling, and Visualization
}, editor = {
Bender, Jan
and
Botsch, Mario
and
Keim, Daniel A.
}, title = {{
Neural Adaptive Scene Tracing (NAScenT)
}}, author = {
Li, Rui
and
Rückert, Darius
and
Wang, Yuanhao
and
Idoughi, Ramzi
and
Heidrich, Wolfgang
}, year = {
2022
}, publisher = {
The Eurographics Association
}, ISBN = {
978-3-03868-189-2
}, DOI = {
10.2312/vmv.20221199
} }
Citation
Collections