Dynamic Mesh-Aware Radiance Fields
Yi-Ling Qiao, Alexander Gao, Yiran Xu, Yue Feng, Jia-Bin Huang, Ming, C. Lin

TL;DR
This paper introduces a system that integrates polygonal meshes with neural radiance fields (NeRF) for photorealistic rendering and dynamic simulation, enabling realistic light transport and interaction in a hybrid graphics pipeline.
Contribution
It presents a novel two-way coupling method between mesh and NeRF, including an efficient algorithm for radiance update, HDR training, and integration with physics simulation for real-time performance.
Findings
Hybrid system improves visual realism in mesh insertion.
Realistic light transport from volumetric NeRF media enhances appearance.
System runs interactively on GPU, supporting complex scene dynamics.
Abstract
Embedding polygonal mesh assets within photorealistic Neural Radience Fields (NeRF) volumes, such that they can be rendered and their dynamics simulated in a physically consistent manner with the NeRF, is under-explored from the system perspective of integrating NeRF into the traditional graphics pipeline. This paper designs a two-way coupling between mesh and NeRF during rendering and simulation. We first review the light transport equations for both mesh and NeRF, then distill them into an efficient algorithm for updating radiance and throughput along a cast ray with an arbitrary number of bounces. To resolve the discrepancy between the linear color space that the path tracer assumes and the sRGB color space that standard NeRF uses, we train NeRF with High Dynamic Range (HDR) images. We also present a strategy to estimate light sources and cast shadows on the NeRF. Finally, we…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputer Graphics and Visualization Techniques · 3D Shape Modeling and Analysis · Advanced Vision and Imaging
