CVPR Findings2026
Stepper: Stepwise Immersive Scene Generation with Multiview Panoramas
Abstract
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° diffusion model that enables consistent, high-resolution expansion, coupled with a geometry reconstruction pipeline that enforces geometric coherence. Trained on a new largescale, multi-view panorama dataset, Stepper achieves stateof-the-art fidelity and structural consistency, outperforming prior approaches, thereby setting a new standard for immersive scene generation.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
- High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Implicit Models
- Adding Conditional Control to Text-to-Image Diffusion Models cites High-Resolution Image Synthesis with Latent Diffusion Models
- Denoising Diffusion Implicit Models cites Denoising Diffusion Probabilistic Models
Builds on46
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations
Related papers
- LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene GenerationShuai Yang, Jing Tan, Mengchen Zhang, Tong Wu et al.SIGGRAPH 2025 · 23 citations
- CubeDiff: Repurposing Diffusion-Based Image Models for Panorama GenerationNikolai Kalischek, Michael Oechsle, Fabian Manhardt, Philipp Henzler et al.ICLR 2025
- DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware DiffusionWeicai Ye, Chenhao Ji, Zheng Chen, Junyao Gao et al.NeurIPS 2024 · 45 citations
- HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene GenerationHaiyang Zhou, Wangbo Yu, Jiawen Guan, Xinhua Cheng et al.ACM MM 2025 · 4 citations
- Taming Stable Diffusion for Text to 360° Panorama Image GenerationCheng Zhang, Qianyi Wu, Camilo Cruz Gambardella, Xiaoshui Huang et al.CVPR 2024 · 27 citations
