Current browse context:
cs.CV
Change to browse by:
References & Citations
Computer Science > Computer Vision and Pattern Recognition
Title: MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures
(Submitted on 30 Jul 2022 (v1), last revised 30 May 2023 (this version, v5))
Abstract: Neural Radiance Fields (NeRFs) have demonstrated amazing ability to synthesize images of 3D scenes from novel views. However, they rely upon specialized volumetric rendering algorithms based on ray marching that are mismatched to the capabilities of widely deployed graphics hardware. This paper introduces a new NeRF representation based on textured polygons that can synthesize novel images efficiently with standard rendering pipelines. The NeRF is represented as a set of polygons with textures representing binary opacities and feature vectors. Traditional rendering of the polygons with a z-buffer yields an image with features at every pixel, which are interpreted by a small, view-dependent MLP running in a fragment shader to produce a final pixel color. This approach enables NeRFs to be rendered with the traditional polygon rasterization pipeline, which provides massive pixel-level parallelism, achieving interactive frame rates on a wide range of compute platforms, including mobile phones.
Submission history
From: Zhiqin Chen [view email][v1] Sat, 30 Jul 2022 17:14:14 GMT (4597kb,D)
[v2] Sat, 6 Aug 2022 10:39:38 GMT (4598kb,D)
[v3] Sat, 19 Nov 2022 03:13:33 GMT (4126kb,D)
[v4] Tue, 21 Mar 2023 20:05:37 GMT (4373kb,D)
[v5] Tue, 30 May 2023 03:49:00 GMT (4374kb,D)
Link back to: arXiv, form interface, contact.