# FastScene: Text-Driven Fast 3D Indoor Scene Generation via Panoramic Gaussian Splatting

arXiv: https://arxiv.org/abs/2405.05768 · HTML: https://mlsanity.com/paper/2405.05768/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 9 May 2024.

## Builds on (most cited first, 30 of 31)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (2021)
- [Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis](https://mlsanity.com/paper/2104.00677/) (2021)
- [Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling](https://mlsanity.com/paper/1908.00222/) (2019)
- [Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models](https://mlsanity.com/paper/2303.11989/) (2023)
- [Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations](https://mlsanity.com/paper/2111.13152/) (2021)
- [NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion](https://mlsanity.com/paper/2302.10109/) (2023)
- [SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image](https://mlsanity.com/paper/2204.00928/) (2022)
- [SceneScape: Text-Driven Consistent Scene Generation](https://mlsanity.com/paper/2302.01133/) (2023)
- [Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields](https://mlsanity.com/paper/2305.11588/) (2023)
- [Anything-3D: Towards Single-view Anything Reconstruction in the Wild](https://mlsanity.com/paper/2304.10261/) (2023)
- [Aggregated Contextual Transformations for High-Resolution Image Inpainting](https://mlsanity.com/paper/2104.01431/) (2021)
- [Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenes](https://mlsanity.com/paper/2303.13450/) (2023)
- [Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints](https://mlsanity.com/paper/2310.03602/) (2023)
- [Diffusion360: Seamless 360 Degree Panoramic Image Generation based on Diffusion Models](https://mlsanity.com/paper/2311.13141/) (2023)
- [Customizing 360-Degree Panoramas through Text-to-Image Diffusion Models](https://mlsanity.com/paper/2310.18840/) (2023)
- [PERF: Panoramic Neural Radiance Field from a Single Panorama](https://mlsanity.com/paper/2310.16831/) (2023)
- [EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation](https://mlsanity.com/paper/2304.07803/) (2023)
- [Reference-guided Controllable Inpainting of Neural Radiance Fields](https://mlsanity.com/paper/2304.09677/) (2023)
- [360FusionNeRF: Panoramic Neural Radiance Fields with Joint Guidance](https://mlsanity.com/paper/2209.14265/) (2022)

## Built on by (most cited first, 24 of 24)

- [Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text](https://mlsanity.com/paper/2406.17601/) (2024)
- [EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing](https://mlsanity.com/paper/2503.10270/) (2025)
- [SceneDreamer360: Text-Driven 3D-Consistent Scene Generation with Panoramic Gaussian Splatting](https://mlsanity.com/paper/2408.13711/) (2024)
- [Splatter-360: Generalizable 360circ Gaussian Splatting for Wide-baseline Panoramic Images](https://mlsanity.com/paper/2412.06250/) (2024)
- [3D Scene Generation: A Survey](https://mlsanity.com/paper/2505.05474/) (2025)
- [A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation](https://mlsanity.com/paper/2508.09977/) (2025)
- [LAYOUTDREAMER: Physics-guided Layout for Text-to-3D Compositional Scene Generation](https://mlsanity.com/paper/2502.01949/) (2025)
- [WorldClaw: Agentic 3D Open-World Generation at Scale](https://mlsanity.com/paper/2608.05248/) (2026)
- [EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching](https://mlsanity.com/paper/2502.20685/) (2025)
- [ADC-GS: Anchor-Driven Deformable and Compressed Gaussian Splatting for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2505.08196/) (2025)
- [FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow](https://mlsanity.com/paper/2603.19598/) (2026)
- [FastPhysGS: Accelerating Physics-based Dynamic 3DGS Simulation via Interior Completion and Adaptive Optimization](https://mlsanity.com/paper/2602.01723/) (2026)
- [SparseGS-W: Sparse-View 3D Gaussian Splatting in the Wild with Generative Priors](https://mlsanity.com/paper/2503.19452/) (2025)
- [GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation](https://mlsanity.com/paper/2511.23191/) (2025)
- [MVRoom: Controllable 3D Indoor Scene Generation with Multi-View Diffusion Models](https://mlsanity.com/paper/2512.04248/) (2025)
- [A Survey on Text-Driven 360-Degree Panorama Generation](https://mlsanity.com/paper/2502.14799/) (2025)
- [Enhancing Monocular 3D Scene Completion with Diffusion Model](https://mlsanity.com/paper/2503.00726/) (2025)
- [Online 3D Gaussian Splatting Modeling with Novel View Selection](https://mlsanity.com/paper/2508.14014/) (2025)
- [Drag4D: Align Your Motion with Text-Driven 3D Scene Generation](https://mlsanity.com/paper/2509.21888/) (2025)
- [Probing CLIP's Comprehension of 360-Degree Textual and Visual Semantics](https://mlsanity.com/paper/2604.24642/) (2026)
- [DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion](https://mlsanity.com/paper/2605.16807/) (2026)
- [FastPano3D: Feed-Forward Indoor Panoramic 3D Reconstruction from a Single Image](https://mlsanity.com/paper/2606.30352/) (2026)
- [Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction](https://mlsanity.com/paper/2607.08769/) (2026)
- [GARO: Geometry-Aware Redundancy Optimization for Real-Time and High-Fidelity Dynamic Gaussian Splatting](https://mlsanity.com/paper/2609.23509/) (2026)

## Abstract (arXiv)

Text-driven 3D indoor scene generation holds broad applications, ranging from gaming and smart homes to AR/VR applications. Fast and high-fidelity scene generation is paramount for ensuring user-friendly experiences. However, existing methods are characterized by lengthy generation processes or necessitate the intricate manual specification of motion parameters, which introduces inconvenience for users. Furthermore, these methods often rely on narrow-field viewpoint iterative generations, compromising global consistency and overall scene quality. To address these issues, we propose FastScene, a framework for fast and higher-quality 3D scene generation, while maintaining the scene consistency. Specifically, given a text prompt, we generate a panorama and estimate its depth, since the panorama encompasses information about the entire scene and exhibits explicit geometric constraints. To obtain high-quality novel views, we introduce the Coarse View Synthesis (CVS) and Progressive Novel View Inpainting (PNVI) strategies, ensuring both scene consistency and view quality. Subsequently, we utilize Multi-View Projection (MVP) to form perspective views, and apply 3D Gaussian Splatting (3DGS) for scene reconstruction. Comprehensive experiments demonstrate FastScene surpasses other methods in both generation speed and quality with better scene consistency. Notably, guided only by a text prompt, FastScene can generate a 3D scene within a mere 15 minutes, which is at least one hour faster than state-of-the-art methods, making it a paradigm for user-friendly scene generation.