将3D场景压缩至150KB，实现跨平台实时渲染。
Plenoptic PNG: Real-Time Neural Radiance Fields in 150 KB
- 用正弦函数索引的密集体素编码全景函数，提升特征共享效率。
- 模型仅150KB，支持在标准GL管线中实时渲染。
- 代码量仅300行，无需额外依赖，适合移动和网页端部署。
本文旨在从2D图像中编码3D场景为极紧凑的表示，并实现其传输、解码与实时渲染，适用于多种平台。尽管NeRF和高斯溅射取得进展，但其庞大的模型尺寸和专用渲染器阻碍了自由视角3D内容如图片般便捷分发。为此，我们设计了一种新型3D表示：将全景函数编码为正弦函数索引的密集体素，促进不同位置间的特征共享，相比传统空间体素更具紧凑性。通过空间分解技术可进一步压缩密集3D特征网格的内存占用。该设计融合空间哈希函数与体素分解优势，使每个3D场景的模型大小小至150 KB。此外，PPNG具备仅300行代码的轻量级渲染管道，能将其表示解码为标准GL纹理和片段着色器，利用传统GL管线实现实时渲染，确保跨平台通用兼容性与高效性，无需额外依赖。
原文摘要 · Abstract (English)
The goal of this paper is to encode a 3D scene into an extremely compact representation from 2D images and to enable its transmittance, decoding and rendering in real-time across various platforms. Despite the progress in NeRFs and Gaussian Splats, their large model size and specialized renderers make it challenging to distribute free-viewpoint 3D content as easily as images. To address this, we have designed a novel 3D representation that encodes the plenoptic function into sinusoidal function indexed dense volumes. This approach facilitates feature sharing across different locations, improving compactness over traditional spatial voxels. The memory footprint of the dense 3D feature grid can be further reduced using spatial decomposition techniques. This design combines the strengths of spatial hashing functions and voxel decomposition, resulting in a model size as small as 150 KB for each 3D scene. Moreover, PPNG features a lightweight rendering pipeline with only 300 lines of code that decodes its representation into standard GL textures and fragment shaders. This enables real-time rendering using the traditional GL pipeline, ensuring universal compatibility and efficiency across various platforms without additional dependencies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。