SphereDiff: Tuning-free 360° Static and Dynamic Panorama Generation via Spherical Latent Representation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914155005476864 |
|---|---|
| author | Park, Minho Kang, Taewoong Yun, Jooyeol Hwang, Sungwon Choo, Jaegul |
| author_facet | Park, Minho Kang, Taewoong Yun, Jooyeol Hwang, Sungwon Choo, Jaegul |
| contents | The increasing demand for AR/VR applications has highlighted the need for high-quality content, such as 360° live wallpapers. However, generating high-quality 360° panoramic contents remains a challenging task due to the severe distortions introduced by equirectangular projection (ERP). Existing approaches either fine-tune pretrained diffusion models on limited ERP datasets or adopt tuning-free methods that still rely on ERP latent representations, often resulting in distracting distortions near the poles. In this paper, we introduce SphereDiff, a novel approach for synthesizing 360° static and live wallpaper with state-of-the-art diffusion models without additional tuning. We define a spherical latent representation that ensures consistent quality across all perspectives, including near the poles. Then, we extend MultiDiffusion to spherical latent representation and propose a dynamic spherical latent sampling method to enable direct use of pretrained diffusion models. Moreover, we introduce distortion-aware weighted averaging to further improve the generation quality. Our method outperforms existing approaches in generating 360° static and live wallpaper, making it a robust solution for immersive AR/VR applications. The code is available here. https://github.com/pmh9960/SphereDiff |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14396 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SphereDiff: Tuning-free 360° Static and Dynamic Panorama Generation via Spherical Latent Representation Park, Minho Kang, Taewoong Yun, Jooyeol Hwang, Sungwon Choo, Jaegul Computer Vision and Pattern Recognition The increasing demand for AR/VR applications has highlighted the need for high-quality content, such as 360° live wallpapers. However, generating high-quality 360° panoramic contents remains a challenging task due to the severe distortions introduced by equirectangular projection (ERP). Existing approaches either fine-tune pretrained diffusion models on limited ERP datasets or adopt tuning-free methods that still rely on ERP latent representations, often resulting in distracting distortions near the poles. In this paper, we introduce SphereDiff, a novel approach for synthesizing 360° static and live wallpaper with state-of-the-art diffusion models without additional tuning. We define a spherical latent representation that ensures consistent quality across all perspectives, including near the poles. Then, we extend MultiDiffusion to spherical latent representation and propose a dynamic spherical latent sampling method to enable direct use of pretrained diffusion models. Moreover, we introduce distortion-aware weighted averaging to further improve the generation quality. Our method outperforms existing approaches in generating 360° static and live wallpaper, making it a robust solution for immersive AR/VR applications. The code is available here. https://github.com/pmh9960/SphereDiff |
| title | SphereDiff: Tuning-free 360° Static and Dynamic Panorama Generation via Spherical Latent Representation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.14396 |