2

Introduction to NeRF

 1 year ago
source link: https://jyzhu.top/Introduction-to-NeRF/
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
neoserver,ios ssh client

This is part of my journey of learning NeRF.

1. Introduction to NeRF

What is NeRF

Reference: Original NeRF paper; an online ariticle

在已知视角下对场景进行一系列的捕获 (包括拍摄到的图像,以及每张图像对应的内外参),合成新视角下的图像。

NeRF 想做这样一件事,不需要中间三维重建的过程,仅根据位姿内参和图像,直接合成新视角下的图像。为此 NeRF 引入了辐射场的概念,这在图形学中是非常重要的概念,在此我们给出渲染方程的定义:

那么辐射和颜色是什么关系呢?简单讲就是,光就是电磁辐射,或者说是振荡的电磁场,光又有波长和频率,波长频率光速波长×频率=光速,光的颜色是由频率决定的,大多数光是不可见的,人眼可见的光谱称为可见光谱,对应的频率就是我们认为的颜色:

SDF - Signed Distance Function

SDF是一种计算图形学中定义距离的函数。SDF定义了空间中的点到隐式曲面的距离,该点在曲面内外决定了其SDF的正负性。

相较于其他像点云(point cloud)、体素(voxel)、面云(mesh)那样的经典3D模型表示方法,SDF有固定的数学方程,更关注物体的表面信息,具有可控的计算成本。

Features of NeRF

  • Representation can be discrete or continuous. but the discrete representation will be a big one if you have more dimensions, e.g., 3 dim.
    • Actually the Plenoxels try to use 3D grids to store the fields. Fast, however, too much memory.
  • Neural Field has advantages:
    1. Compactness 紧致:
    2. Regularization: nn itself as inductive bias makes it easy to learn
    3. Domain Agonostic: cheap to add a dimension
  • also problems
    • Editability / Manipulability
    • Computational Complexity
    • Spectral Bias

Problem Formulation

  • Input: multiview images
  • Output: 3D Geometry and appearance
  • Objective:

arg⁡minx‖y−F(x)‖+λP(x)

y is multiview images, F is forward mapping, x is the desired 3D reconstruction.

F can be differentiable, then you can supervise this.

  • nn本身就是某种constraints,你就不需要加太多handicraft constraints

About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK