Tiled Multiplane Images for Practical 3D Photography

TL;DR

This paper introduces Tiled Multiplane Images (TMPI), a novel approach that divides a scene into smaller regions with fewer depth layers, enabling efficient and high-quality 3D view synthesis from a single image.

Contribution

The paper presents a new tiled MPI representation with adaptive depth planes, reducing redundancy and computational cost while maintaining high-quality view synthesis.

Findings

Comparable quality to state-of-the-art MPI methods

Lower computational overhead

Effective in real-world single-view 3D photography

Abstract

The task of synthesizing novel views from a single image has useful applications in virtual reality and mobile computing, and a number of approaches to the problem have been proposed in recent years. A Multiplane Image (MPI) estimates the scene as a stack of RGBA layers, and can model complex appearance effects, anti-alias depth errors and synthesize soft edges better than methods that use textured meshes or layered depth images. And unlike neural radiance fields, an MPI can be efficiently rendered on graphics hardware. However, MPIs are highly redundant and require a large number of depth layers to achieve plausible results. Based on the observation that the depth complexity in local image regions is lower than that over the entire image, we split an MPI into many small, tiled regions, each with only a few depth planes. We call this representation a Tiled Multiplane Image (TMPI). We propose a method for generating a TMPI with adaptive depth planes for single-view 3D photography in the wild. Our synthesized results are comparable to state-of-the-art single-view MPI methods while having lower computational overhead.