VALSE 论文速览 第201期：Spiking NeRF: 基于非连续表示的真实世界几何形态表征 ...

论文题目：

Spiking NeRF: Representing the Real-World Geometry by a Discontinuous Representation

作者列表：

廖展锋 (浙江大学)、刘彦 (浙江大学)、郑乾 (浙江大学）、潘纲 (浙江大学)

B站观看网址：

https://www.bilibili.com/video/BV1fSxNeNEiB/?spm_id_from=333.999.0.0&vd_source=2044ac986b5caa4c8b5f00b525441df3

复制链接到浏览器打开或点击阅读原文即可跳转至观看页面。

论文摘要：

A crucial reason for the success of existing NeRF-based methods is to build a neural density field for the geometry representation via multiple perceptron layers (MLPs). MLPs are continuous functions, however, real geometry or density field is frequently discontinuous at the interface between the air and the surface. Such a contrary brings the problem of unfaithful geometry representation. To this end, this paper proposes spiking NeRF, which leverages spiking neurons and a hybrid Artificial Neural Network (ANN)-Spiking Neural Network (SNN) framework to build a discontinuous density field for faithful geometry representation. Specifically, we first demonstrate the reason why continuous density fields will bring inaccuracy. Then, we propose to use the spiking neurons to build a discontinuous density field. We conduct a comprehensive analysis for the problem of existing spiking neuron models and then provide the numerical relationship between the parameter of the spiking neuron and the theoretical accuracy of geometry. Based on this, we propose a bounded spiking neuron to build the discontinuous density field.

参考文献：

[1] Liao, Zhanfeng, Qian Zheng, Yan Liu, and Gang Pan. "Spiking NeRF: Representing the Real-World Geometry by a Discontinuous Representation." AAAI, 2024.

论文链接：

[https://arxiv.org/abs/2311.09077]

代码链接：

[https://github.com/liaozhanfeng/Spiking-NeRF]

视频讲者简介：

廖展锋，浙江大学硕士生，潘纲教授团队。研究方向为类脑计算、三维视觉，曾在计算机视觉顶会AAAI发表工作(oral)。

个人主页：

https://github.com/liaozhanfeng

特别鸣谢本次论文速览主要组织者：

月度轮值AC：傅雪阳 (中国科学技术大学)