OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Huang, Yukun, Yu, Jiwen, Zhou, Yanning, Wang, Jianan, Wang, Xintao, Wan, Pengfei, Liu, Xihui
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918179469524992
author Huang, Yukun
Yu, Jiwen
Zhou, Yanning
Wang, Jianan
Wang, Xintao
Wan, Pengfei
Liu, Xihui
author_facet Huang, Yukun
Yu, Jiwen
Zhou, Yanning
Wang, Jianan
Wang, Xintao
Wan, Pengfei
Liu, Xihui
contents There are two prevalent ways to constructing 3D scenes: procedural generation and 2D lifting. Among them, panorama-based 2D lifting has emerged as a promising technique, leveraging powerful 2D generative priors to produce immersive, realistic, and diverse 3D environments. In this work, we advance this technique to generate graphics-ready 3D scenes suitable for physically based rendering (PBR), relighting, and simulation. Our key insight is to repurpose 2D generative models for panoramic perception of geometry, textures, and PBR materials. Unlike existing 2D lifting approaches that emphasize appearance generation and ignore the perception of intrinsic properties, we present OmniX, a versatile and unified framework. Based on a lightweight and efficient cross-modal adapter structure, OmniX reuses 2D generative priors for a broad range of panoramic vision tasks, including panoramic perception, generation, and completion. Furthermore, we construct a large-scale synthetic panorama dataset containing high-quality multimodal panoramas from diverse indoor and outdoor scenes. Extensive experiments demonstrate the effectiveness of our model in panoramic visual perception and graphics-ready 3D scene generation, opening new possibilities for immersive and physically realistic virtual world generation.
format Preprint
id arxiv_https___arxiv_org_abs_2510_26800
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes
Huang, Yukun
Yu, Jiwen
Zhou, Yanning
Wang, Jianan
Wang, Xintao
Wan, Pengfei
Liu, Xihui
Computer Vision and Pattern Recognition
Graphics
Machine Learning
There are two prevalent ways to constructing 3D scenes: procedural generation and 2D lifting. Among them, panorama-based 2D lifting has emerged as a promising technique, leveraging powerful 2D generative priors to produce immersive, realistic, and diverse 3D environments. In this work, we advance this technique to generate graphics-ready 3D scenes suitable for physically based rendering (PBR), relighting, and simulation. Our key insight is to repurpose 2D generative models for panoramic perception of geometry, textures, and PBR materials. Unlike existing 2D lifting approaches that emphasize appearance generation and ignore the perception of intrinsic properties, we present OmniX, a versatile and unified framework. Based on a lightweight and efficient cross-modal adapter structure, OmniX reuses 2D generative priors for a broad range of panoramic vision tasks, including panoramic perception, generation, and completion. Furthermore, we construct a large-scale synthetic panorama dataset containing high-quality multimodal panoramas from diverse indoor and outdoor scenes. Extensive experiments demonstrate the effectiveness of our model in panoramic visual perception and graphics-ready 3D scene generation, opening new possibilities for immersive and physically realistic virtual world generation.
title OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes
topic Computer Vision and Pattern Recognition
Graphics
Machine Learning
url https://arxiv.org/abs/2510.26800