MixRT: Mixed Neural Representations For Real-Time NeRF Rendering

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Chaojian, Wu, Bichen, Vajda, Peter, Lin, Yingyan Celine
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912298010935296
author Li, Chaojian
Wu, Bichen
Vajda, Peter
Lin, Yingyan Celine
author_facet Li, Chaojian
Wu, Bichen
Vajda, Peter
Lin, Yingyan Celine
contents Neural Radiance Field (NeRF) has emerged as a leading technique for novel view synthesis, owing to its impressive photorealistic reconstruction and rendering capability. Nevertheless, achieving real-time NeRF rendering in large-scale scenes has presented challenges, often leading to the adoption of either intricate baked mesh representations with a substantial number of triangles or resource-intensive ray marching in baked representations. We challenge these conventions, observing that high-quality geometry, represented by meshes with substantial triangles, is not necessary for achieving photorealistic rendering quality. Consequently, we propose MixRT, a novel NeRF representation that includes a low-quality mesh, a view-dependent displacement map, and a compressed NeRF model. This design effectively harnesses the capabilities of existing graphics hardware, thus enabling real-time NeRF rendering on edge devices. Leveraging a highly-optimized WebGL-based rendering framework, our proposed MixRT attains real-time rendering speeds on edge devices (over 30 FPS at a resolution of 1280 x 720 on a MacBook M1 Pro laptop), better rendering quality (0.2 PSNR higher in indoor scenes of the Unbounded-360 datasets), and a smaller storage size (less than 80% compared to state-of-the-art methods).
format Preprint
id arxiv_https___arxiv_org_abs_2312_11841
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle MixRT: Mixed Neural Representations For Real-Time NeRF Rendering
Li, Chaojian
Wu, Bichen
Vajda, Peter
Lin, Yingyan Celine
Computer Vision and Pattern Recognition
Neural Radiance Field (NeRF) has emerged as a leading technique for novel view synthesis, owing to its impressive photorealistic reconstruction and rendering capability. Nevertheless, achieving real-time NeRF rendering in large-scale scenes has presented challenges, often leading to the adoption of either intricate baked mesh representations with a substantial number of triangles or resource-intensive ray marching in baked representations. We challenge these conventions, observing that high-quality geometry, represented by meshes with substantial triangles, is not necessary for achieving photorealistic rendering quality. Consequently, we propose MixRT, a novel NeRF representation that includes a low-quality mesh, a view-dependent displacement map, and a compressed NeRF model. This design effectively harnesses the capabilities of existing graphics hardware, thus enabling real-time NeRF rendering on edge devices. Leveraging a highly-optimized WebGL-based rendering framework, our proposed MixRT attains real-time rendering speeds on edge devices (over 30 FPS at a resolution of 1280 x 720 on a MacBook M1 Pro laptop), better rendering quality (0.2 PSNR higher in indoor scenes of the Unbounded-360 datasets), and a smaller storage size (less than 80% compared to state-of-the-art methods).
title MixRT: Mixed Neural Representations For Real-Time NeRF Rendering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.11841