HORIZON: High-Resolution Semantically Controlled Panorama Synthesis

TL;DR

This paper introduces HORIZON, a novel framework for high-resolution, semantically controlled panorama synthesis that effectively addresses spherical distortion and edge discontinuity, enabling more realistic and customizable 360-degree visual landscapes.

Contribution

The paper presents a new spherical modeling approach combined with parallel decoding, allowing high-resolution panorama generation with semantic control via image and text inputs.

Findings

Outperforms recent methods in quantitative metrics

Produces higher quality and more realistic panoramas

Effectively handles spherical distortion and edge issues

Abstract

Panorama synthesis endeavors to craft captivating 360-degree visual landscapes, immersing users in the heart of virtual worlds. Nevertheless, contemporary panoramic synthesis techniques grapple with the challenge of semantically guiding the content generation process. Although recent breakthroughs in visual synthesis have unlocked the potential for semantic control in 2D flat images, a direct application of these methods to panorama synthesis yields distorted content. In this study, we unveil an innovative framework for generating high-resolution panoramas, adeptly addressing the issues of spherical distortion and edge discontinuity through sophisticated spherical modeling. Our pioneering approach empowers users with semantic control, harnessing both image and text inputs, while concurrently streamlining the generation of high-resolution panoramas using parallel decoding. We rigorously evaluate our methodology on a diverse array of indoor and outdoor datasets, establishing its superiority over recent related work, in terms of both quantitative and qualitative performance metrics. Our research elevates the controllability, efficiency, and fidelity of panorama synthesis to new levels.