View Synthesis of Dynamic Scenes based on Deep 3D Mask Volume

TL;DR

This paper introduces a new dataset and a deep learning method for synthesizing stable, photorealistic views of dynamic scenes from multiple camera videos, addressing challenges of temporal consistency and scene complexity.

Contribution

The paper presents a novel Deep 3D Mask Volume algorithm and a high-quality multi-view video dataset for dynamic scene view synthesis.

Findings

Achieves improved temporal stability over existing methods.

Produces view synthesis videos with minimal flickering artifacts.

Enables larger translational movements in synthesized views.

Abstract

Image view synthesis has seen great success in reconstructing photorealistic visuals, thanks to deep learning and various novel representations. The next key step in immersive virtual experiences is view synthesis of dynamic scenes. However, several challenges exist due to the lack of high-quality training datasets, and the additional time dimension for videos of dynamic scenes. To address this issue, we introduce a multi-view video dataset, captured with a custom 10-camera rig in 120FPS. The dataset contains 96 high-quality scenes showing various visual effects and human interactions in outdoor scenes. We develop a new algorithm, Deep 3D Mask Volume, which enables temporally-stable view extrapolation from binocular videos of dynamic scenes, captured by static cameras. Our algorithm addresses the temporal inconsistency of disocclusions by identifying the error-prone areas with a 3D mask volume, and replaces them with static background observed throughout the video. Our method enables manipulation in 3D space as opposed to simple 2D masks, We demonstrate better temporal stability than frame-by-frame static view synthesis methods, or those that use 2D masks. The resulting view synthesis videos show minimal flickering artifacts and allow for larger translational movements.