Dream360: Diverse and Immersive Outdoor Virtual Scene Creation via Transformer-Based 360 Image Outpainting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ai, Hao, Cao, Zidong, Lu, Haonan, Chen, Chen, Ma, Jian, Zhou, Pengyuan, Kim, Tae-Kyun, Hui, Pan, Wang, Lin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910302764793856
author Ai, Hao
Cao, Zidong
Lu, Haonan
Chen, Chen
Ma, Jian
Zhou, Pengyuan
Kim, Tae-Kyun
Hui, Pan
Wang, Lin
author_facet Ai, Hao
Cao, Zidong
Lu, Haonan
Chen, Chen
Ma, Jian
Zhou, Pengyuan
Kim, Tae-Kyun
Hui, Pan
Wang, Lin
contents 360 images, with a field-of-view (FoV) of 180x360, provide immersive and realistic environments for emerging virtual reality (VR) applications, such as virtual tourism, where users desire to create diverse panoramic scenes from a narrow FoV photo they take from a viewpoint via portable devices. It thus brings us to a technical challenge: `How to allow the users to freely create diverse and immersive virtual scenes from a narrow FoV image with a specified viewport?' To this end, we propose a transformer-based 360 image outpainting framework called Dream360, which can generate diverse, high-fidelity, and high-resolution panoramas from user-selected viewports, considering the spherical properties of 360 images. Compared with existing methods, e.g., [3], which primarily focus on inputs with rectangular masks and central locations while overlooking the spherical property of 360 images, our Dream360 offers higher outpainting flexibility and fidelity based on the spherical representation. Dream360 comprises two key learning stages: (I) codebook-based panorama outpainting via Spherical-VQGAN (S-VQGAN), and (II) frequency-aware refinement with a novel frequency-aware consistency loss. Specifically, S-VQGAN learns a sphere-specific codebook from spherical harmonic (SH) values, providing a better representation of spherical data distribution for scene modeling. The frequency-aware refinement matches the resolution and further improves the semantic consistency and visual fidelity of the generated results. Our Dream360 achieves significantly lower Frechet Inception Distance (FID) scores and better visual fidelity than existing methods. We also conducted a user study involving 15 participants to interactively evaluate the quality of the generated results in VR, demonstrating the flexibility and superiority of our Dream360 framework.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10564
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dream360: Diverse and Immersive Outdoor Virtual Scene Creation via Transformer-Based 360 Image Outpainting
Ai, Hao
Cao, Zidong
Lu, Haonan
Chen, Chen
Ma, Jian
Zhou, Pengyuan
Kim, Tae-Kyun
Hui, Pan
Wang, Lin
Computer Vision and Pattern Recognition
Human-Computer Interaction
360 images, with a field-of-view (FoV) of 180x360, provide immersive and realistic environments for emerging virtual reality (VR) applications, such as virtual tourism, where users desire to create diverse panoramic scenes from a narrow FoV photo they take from a viewpoint via portable devices. It thus brings us to a technical challenge: `How to allow the users to freely create diverse and immersive virtual scenes from a narrow FoV image with a specified viewport?' To this end, we propose a transformer-based 360 image outpainting framework called Dream360, which can generate diverse, high-fidelity, and high-resolution panoramas from user-selected viewports, considering the spherical properties of 360 images. Compared with existing methods, e.g., [3], which primarily focus on inputs with rectangular masks and central locations while overlooking the spherical property of 360 images, our Dream360 offers higher outpainting flexibility and fidelity based on the spherical representation. Dream360 comprises two key learning stages: (I) codebook-based panorama outpainting via Spherical-VQGAN (S-VQGAN), and (II) frequency-aware refinement with a novel frequency-aware consistency loss. Specifically, S-VQGAN learns a sphere-specific codebook from spherical harmonic (SH) values, providing a better representation of spherical data distribution for scene modeling. The frequency-aware refinement matches the resolution and further improves the semantic consistency and visual fidelity of the generated results. Our Dream360 achieves significantly lower Frechet Inception Distance (FID) scores and better visual fidelity than existing methods. We also conducted a user study involving 15 participants to interactively evaluate the quality of the generated results in VR, demonstrating the flexibility and superiority of our Dream360 framework.
title Dream360: Diverse and Immersive Outdoor Virtual Scene Creation via Transformer-Based 360 Image Outpainting
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2401.10564