Exploring Dynamic Novel View Synthesis Technologies for Cinematography
This work addresses cinematographers needing to choose models for creating new shots, but it is incremental as it focuses on exploration rather than introducing new methods.
The paper tackles the problem of selecting models for dynamic novel view synthesis in cinematography by exploring technologies like Neural Radiance Fields and Gaussian Splatting, and demonstrates their potential through a filmed montage using various models.
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.