A Portable Multiscopic Camera for Novel View and Time Synthesis in Dynamic Scenes (IROS 2022)

Our implementation is based on nerfmm(PyTorch)

A Portable Multiscopic Camera for Novel View and Time Synthesis in Dynamic Scenes
https://yuenfuilau.github.io/

paper | project website | demo video

Introduction

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.

To Do

• Release the inference code
• Release the pretrained model
• Writing Descriptions
• Release the training code

Set up

Installation

git clone https://github.com/YuenFuiLau/A-Portable-Multiscopic-Camera-for-Novel-View-and-Time-Synthesis-in-Dynamic-Scenes.git
cd A-Portable-Multiscopic-Camera-for-Novel-View-and-Time-Synthesis-in-Dynamic-Scenes

Environment

The environment can be simply set up from the provided environment.yml:

conda env create -f environment.yml

More Results

Acknowledgement

Thanks to nerfmm(PyTorch) for sharing their code.