探索动态新视角合成技术在影视制作中的应用与模型选型
Exploring Dynamic Novel View Synthesis Technologies for Cinematography
- 对比NeRF与高斯泼溅实现动态新视角合成
- 实拍短片展示多种模型生成效果差异
- 适合影视后期与虚拟制片从业者参考
新视角合成（NVS）在影视制作中展现出巨大潜力，尤其通过神经辐射场（NeRF）和高斯泼溅（GS）技术建模真实3D场景，可生成现实中难以拍摄的镜头，如复杂布景或昂贵设备限制下的画面。该技术还支持平滑摄像机运动、虚拟重拍、慢动作等特效。本文探讨动态NVS技术，旨在帮助模型选型。通过一段使用多种NVS模型拍摄的短片蒙太奇，展示其实际应用潜力。
原文摘要 · Abstract (English)
Novel view synthesis (NVS) has shown significant promise for applications in cinematographic production, particularly through the exploitation of Neural Radiance Fields (NeRF) and Gaussian Splatting (GS). These methods model real 3D scenes, enabling the creation of new shots that are challenging to capture in the real world due to set topology or expensive equipment requirement. This innovation also offers cinematographic advantages such as smooth camera movements, virtual re-shoots, slow-motion effects, etc. This paper explores dynamic NVS with the aim of facilitating the model selection process. We showcase its potential through a short montage filmed using various NVS models.
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。