A Portable Multiscopic Camera for Novel View and Time Synthesis in Dynamic Scenes

TL;DR

This paper introduces a portable multiscopic camera system that, combined with a neural radiance field model, enables high-quality novel view and time synthesis in dynamic scenes, outperforming existing methods.

Contribution

The work presents a physical multiscopic camera with five cameras and a novel neural radiance field model for dynamic scenes, including camera parameter optimization and temporal interpolation modules.

Findings

Outperforms alternative solutions qualitatively and quantitatively

Successfully synthesizes novel views and times in dynamic scenes

Demonstrates effectiveness on real-world and synthetic datasets

Abstract

We present a portable multiscopic camera system with a dedicated model for novel view and time synthesis in dynamic scenes. Our goal is to render high-quality images for a dynamic scene from any viewpoint at any time using our portable multiscopic camera. To achieve such novel view and time synthesis, we develop a physical multiscopic camera equipped with five cameras to train a neural radiance field (NeRF) in both time and spatial domains for dynamic scenes. Our model maps a 6D coordinate (3D spatial position, 1D temporal coordinate, and 2D viewing direction) to view-dependent and time-varying emitted radiance and volume density. Volume rendering is applied to render a photo-realistic image at a specified camera pose and time. To improve the robustness of our physical camera, we propose a camera parameter optimization module and a temporal frame interpolation module to promote information propagation across time. We conduct experiments on both real-world and synthetic datasets to evaluate our system, and the results show that our approach outperforms alternative solutions qualitatively and quantitatively. Our code and dataset are available at https://yuenfuilau.github.io.