Relighting Scenes with Object Insertions in Neural Radiance Fields

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Xuening, Yi, Renjiao, Wen, Xin, Zhu, Chenyang, Xu, Kai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929393587191808
author Zhu, Xuening
Yi, Renjiao
Wen, Xin
Zhu, Chenyang
Xu, Kai
author_facet Zhu, Xuening
Yi, Renjiao
Wen, Xin
Zhu, Chenyang
Xu, Kai
contents The insertion of objects into a scene and relighting are commonly utilized applications in augmented reality (AR). Previous methods focused on inserting virtual objects using CAD models or real objects from single-view images, resulting in highly limited AR application scenarios. We propose a novel NeRF-based pipeline for inserting object NeRFs into scene NeRFs, enabling novel view synthesis and realistic relighting, supporting physical interactions like casting shadows onto each other, from two sets of images depicting the object and scene. The lighting environment is in a hybrid representation of Spherical Harmonics and Spherical Gaussians, representing both high- and low-frequency lighting components very well, and supporting non-Lambertian surfaces. Specifically, we leverage the benefits of volume rendering and introduce an innovative approach for efficient shadow rendering by comparing the depth maps between the camera view and the light source view and generating vivid soft shadows. The proposed method achieves realistic relighting effects in extensive experimental evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2406_14806
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Relighting Scenes with Object Insertions in Neural Radiance Fields
Zhu, Xuening
Yi, Renjiao
Wen, Xin
Zhu, Chenyang
Xu, Kai
Computer Vision and Pattern Recognition
Graphics
The insertion of objects into a scene and relighting are commonly utilized applications in augmented reality (AR). Previous methods focused on inserting virtual objects using CAD models or real objects from single-view images, resulting in highly limited AR application scenarios. We propose a novel NeRF-based pipeline for inserting object NeRFs into scene NeRFs, enabling novel view synthesis and realistic relighting, supporting physical interactions like casting shadows onto each other, from two sets of images depicting the object and scene. The lighting environment is in a hybrid representation of Spherical Harmonics and Spherical Gaussians, representing both high- and low-frequency lighting components very well, and supporting non-Lambertian surfaces. Specifically, we leverage the benefits of volume rendering and introduce an innovative approach for efficient shadow rendering by comparing the depth maps between the camera view and the light source view and generating vivid soft shadows. The proposed method achieves realistic relighting effects in extensive experimental evaluations.
title Relighting Scenes with Object Insertions in Neural Radiance Fields
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2406.14806