Depth self-supervision for single image novel view synthesis

TL;DR

This paper introduces a self-supervised framework that jointly optimizes for novel view synthesis and depth estimation from a single image, leading to improved image quality and depth accuracy.

Contribution

It proposes a shared depth decoder trained in a self-supervised manner to enhance both view synthesis and depth estimation simultaneously.

Findings

Higher-quality generated images

More accurate depth maps for target views

Effective joint optimization of view synthesis and depth estimation

Abstract

In this paper, we tackle the problem of generating a novel image from an arbitrary viewpoint given a single frame as input. While existing methods operating in this setup aim at predicting the target view depth map to guide the synthesis, without explicit supervision over such a task, we jointly optimize our framework for both novel view synthesis and depth estimation to unleash the synergy between the two at its best. Specifically, a shared depth decoder is trained in a self-supervised manner to predict depth maps that are consistent across the source and target views. Our results demonstrate the effectiveness of our approach in addressing the challenges of both tasks allowing for higher-quality generated images, as well as more accurate depth for the target viewpoint.