# Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration

arXiv: https://arxiv.org/abs/2504.00387 · HTML: https://mlsanity.com/paper/2504.00387/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 59 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 30 of 43)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023)
- [MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images](https://mlsanity.com/paper/2403.14627/) (2024)
- [One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization](https://mlsanity.com/paper/2306.16928/) (2023)
- [Point-NeRF: Point-based Neural Radiance Fields](https://mlsanity.com/paper/2201.08845/) (2022)
- [Compact 3D Gaussian Representation for Radiance Field](https://mlsanity.com/paper/2311.13681/) (2023)
- [DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes](https://mlsanity.com/paper/2312.07920/) (2023)
- [OneFormer: One Transformer to Rule Universal Image Segmentation](https://mlsanity.com/paper/2211.06220/) (2022)
- [Inversion-Based Style Transfer with Diffusion Models](https://mlsanity.com/paper/2211.13203/) (2022)
- [Generative Novel View Synthesis with 3D-Aware Diffusion Models](https://mlsanity.com/paper/2304.02602/) (2023)
- [DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization](https://mlsanity.com/paper/2403.06912/) (2024)
- [Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference](https://mlsanity.com/paper/1902.10556/) (2019)
- [Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models](https://mlsanity.com/paper/2303.11989/) (2023)
- [LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes](https://mlsanity.com/paper/2311.13384/) (2023)
- [VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction](https://mlsanity.com/paper/2402.17427/) (2024)
- [WonderWorld: Interactive 3D Scene Generation from a Single Image](https://mlsanity.com/paper/2406.09394/) (2024)
- [NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo](https://mlsanity.com/paper/2109.01129/) (2021)
- [CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians](https://mlsanity.com/paper/2404.01133/) (2024)
- [SceneScape: Text-Driven Consistent Scene Generation](https://mlsanity.com/paper/2302.01133/) (2023)

## Built on by (most cited first, 11 of 11)

- [HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels](https://mlsanity.com/paper/2507.21809/) (2025)
- [A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation](https://mlsanity.com/paper/2508.09977/) (2025)
- [WorldClaw: Agentic 3D Open-World Generation at Scale](https://mlsanity.com/paper/2608.05248/) (2026)
- [MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts](https://mlsanity.com/paper/2511.20415/) (2025)
- [AnchoredDream: Zero-Shot 360deg Indoor Scene Generation from a Single View via Geometric Grounding](https://mlsanity.com/paper/2601.16532/) (2026)
- [RoomPlanner: Explicit Layout Planner for Easier LLM-Driven 3D Room Generation](https://mlsanity.com/paper/2511.17048/) (2025)
- [PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban Scenes](https://mlsanity.com/paper/2506.19117/) (2025)
- [CylinderSplat: 3D Gaussian Splatting with Cylindrical Triplanes for Panoramic Novel View Synthesis](https://mlsanity.com/paper/2603.05882/) (2026)
- [Top2Pano: Learning to Generate Indoor Panoramas from Top-Down View](https://mlsanity.com/paper/2507.21371/) (2025)
- [Toward 360-Degree Indoor Panorama Editing via Tuning-Free Diffusion Model with Refocusing Cross-Attention](https://mlsanity.com/paper/2606.14035/) (2026)
- [Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction](https://mlsanity.com/paper/2607.08769/) (2026)

## Abstract (arXiv)

The reconstruction of immersive and realistic 3D scenes holds significant practical importance in various fields of computer vision and computer graphics. Typically, immersive and realistic scenes should be free from obstructions by dynamic objects, maintain global texture consistency, and allow for unrestricted exploration. The current mainstream methods for image-driven scene construction involves iteratively refining the initial image using a moving virtual camera to generate the scene. However, previous methods struggle with visual discontinuities due to global texture inconsistencies under varying camera poses, and they frequently exhibit scene voids caused by foreground-background occlusions. To this end, we propose a novel layered 3D scene reconstruction framework from panoramic image, named Scene4U. Specifically, Scene4U integrates an open-vocabulary segmentation model with a large language model to decompose a real panorama into multiple layers. Then, we employs a layered repair module based on diffusion model to restore occluded regions using visual cues and depth information, generating a hierarchical representation of the scene. The multi-layer panorama is then initialized as a 3D Gaussian Splatting representation, followed by layered optimization, which ultimately produces an immersive 3D scene with semantic and structural consistency that supports free exploration. Scene4U outperforms state-of-the-art method, improving by 24.24% in LPIPS and 24.40% in BRISQUE, while also achieving the fastest training speed. Additionally, to demonstrate the robustness of Scene4U and allow users to experience immersive scenes from various landmarks, we build WorldVista3D dataset for 3D scene reconstruction, which contains panoramic images of globally renowned sites. The implementation code and dataset will be released at https://github.com/LongHZ140516/Scene4U .