【ECCV 2020 (oral)】NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

【ECCV 2020 _oral】NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

• 一、前言
• Abstract
• 1 Introduction
• 2 Related Work
• 3 Neural Radiance Field Scene Representation
• 4 Volume Rendering with Radiance Fields
• 5 Optimizing a Neural Radiance Field
• • 5.1 Positional encoding
  • 5.2 Hierarchical volume sampling
  • 5.3 Implementation details
• 6 Results
• • 6.1 Datasets
  • 6.2 Comparisons
  • 6.3 Discussion
  • 6.4 Ablation studies
• 7 Conclusion
• A Additional Implementation Details
• B Additional Baseline Method Details
• C NDC ray space derivation
• D Additional Results

一、前言

Authors: Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik, Jonathan T. Barron, Ravi Ramamoorthi, Ren Ng

【Paper】 > 【Github_Code】 > 【Project】

Abstract

介绍：我们提出了一种方法，通过使用稀疏的输入视图集优化底层连续体积场景函数，实现合成复杂场景的新颖视图的最先进的结果。
方法：我们的算法使用全连接（非卷积）深度网络表示场景，其输入是单个连续 5D 坐标（空间位置 ( x , y , z ) (x,y,z)