Semantic View Synthesis

TL;DR

This paper introduces a novel semantic view synthesis method that generates high-quality, geometrically consistent novel view renderings from semantic label maps by combining surface synthesis with explicit MPI constraints.

Contribution

It proposes a two-step approach that synthesizes surface color and depth, then uses these to guide MPI prediction, improving view consistency and rendering quality.

Findings

Produces sharp, high-quality novel view images

Achieves better geometric consistency than baselines

Effective on diverse indoor and outdoor scenes

Abstract

We tackle a new problem of semantic view synthesis -- generating free-viewpoint rendering of a synthesized scene using a semantic label map as input. We build upon recent advances in semantic image synthesis and view synthesis for handling photographic image content generation and view extrapolation. Direct application of existing image/view synthesis methods, however, results in severe ghosting/blurry artifacts. To address the drawbacks, we propose a two-step approach. First, we focus on synthesizing the color and depth of the visible surface of the 3D scene. We then use the synthesized color and depth to impose explicit constraints on the multiple-plane image (MPI) representation prediction process. Our method produces sharp contents at the original view and geometrically consistent renderings across novel viewpoints. The experiments on numerous indoor and outdoor images show favorable results against several strong baselines and validate the effectiveness of our approach.