The synthesis of immersive 3D scenes from text is rapidly maturing, driven by novel video generative models and feed-forward 3D reconstruction, with vast potential in AR/VR and world modeling. While panoramic images have proven effective for scene initialization, existing approaches suffer from a trade-off between visual fidelity and explorability: autoregressive expansion suffers from context drift, while panoramic video generation is limited to low resolution. We present Stepper, a unified framework for text-driven immersive 3D scene synthesis that circumvents these limitations via stepwise panoramic scene expansion. Stepper leverages a novel multi-view 360{\deg} diffusion model that enables consistent, high-resolution expansion, coupled with a geometry reconstruction pipeline that enforces geometric coherence. Trained on a new large-scale, multi-view panorama dataset, Stepper achieves state-of-the-art fidelity and structural consistency, outperforming prior approaches, thereby setting a new standard for immersive scene generation.
@article{arxiv.2603.28980,
title = {Stepper: Stepwise Immersive Scene Generation with Multiview Panoramas},
author = {Felix Wimbauer and Fabian Manhardt and Michael Oechsle and Nikolai Kalischek and Christian Rupprecht and Daniel Cremers and Federico Tombari},
journal= {arXiv preprint arXiv:2603.28980},
year = {2026}
}
Comments
Accepted at CVPR 2026 Findings; Find our project page under https://fwmb.github.io/stepper/