# Text2Scene: Text-driven Indoor Scene Stylization with Part-aware Details

arXiv: https://arxiv.org/abs/2308.16880 · HTML: https://mlsanity.com/paper/2308.16880/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 61 references that are in the map.
- First posted on arXiv 31 Aug 2023.

## Builds on (most cited first, 30 of 50)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [Zero-Shot Text-Guided Object Generation with Dream Fields](https://mlsanity.com/paper/2112.01455/) (2021)
- [Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures](https://mlsanity.com/paper/2211.07600/) (2022)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [Decomposing NeRF for Editing via Feature Field Distillation](https://mlsanity.com/paper/2205.15585/) (2022)
- [CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields](https://mlsanity.com/paper/2112.05139/) (2021)
- [ABO: Dataset and Benchmarks for Real-World 3D Object Understanding](https://mlsanity.com/paper/2110.06199/) (2021)
- [Text2Mesh: Text-Driven Neural Stylization for Meshes](https://mlsanity.com/paper/2112.03221/) (2021)
- [Neural RGB-D Surface Reconstruction](https://mlsanity.com/paper/2104.04532/) (2021)
- [Text2LIVE: Text-Driven Layered Image and Video Editing](https://mlsanity.com/paper/2204.02491/) (2022)
- [3D-FUTURE: 3D Furniture shape with TextURE](https://mlsanity.com/paper/2009.09633/) (2020)
- [CLIP-Mesh: Generating textured meshes from text using pretrained image-text models](https://mlsanity.com/paper/2203.13333/) (2022)
- [CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation](https://mlsanity.com/paper/2110.02624/) (2021)
- [Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer](https://mlsanity.com/paper/1908.01210/) (2019)

## Built on by (most cited first, 18 of 18)

- [Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning](https://mlsanity.com/paper/2403.11401/) (2024)
- [AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes](https://mlsanity.com/paper/2312.06644/) (2023)
- [DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling](https://mlsanity.com/paper/2404.03575/) (2024)
- [3D Scene Generation: A Survey](https://mlsanity.com/paper/2505.05474/) (2025)
- [Gaussian Splatting in Style](https://mlsanity.com/paper/2403.08498/) (2024)
- [RoomTex: Texturing Compositional Indoor Scenes via Iterative Inpainting](https://mlsanity.com/paper/2406.02461/) (2024)
- [Advances in 3D Neural Stylization: A Survey](https://mlsanity.com/paper/2311.18328/) (2023)
- [Scene123: One Prompt to 3D Scene Generation via Video-Assisted and Consistency-Enhanced MAE](https://mlsanity.com/paper/2408.05477/) (2024)
- [SpatialMosaic: A Multiview VLM Dataset for Partial Visibility](https://mlsanity.com/paper/2512.23365/) (2025)
- [3DStyleGLIP: Part-Tailored Text-Guided 3D Neural Stylization](https://mlsanity.com/paper/2404.02634/) (2024)
- [HLG: Comprehensive 3D Room Construction via Hierarchical Layout Generation](https://mlsanity.com/paper/2508.17832/) (2025)
- [MeshFeat: Multi-Resolution Features for Neural Fields on Meshes](https://mlsanity.com/paper/2407.13592/) (2024)
- [IP-FaceDiff: Identity-Preserving Facial Video Editing with Diffusion](https://mlsanity.com/paper/2501.07530/) (2025)
- [StyleCity: Large-Scale 3D Urban Scenes Stylization](https://mlsanity.com/paper/2404.10681/) (2024)
- [Style-Consistent 3D Indoor Scene Synthesis with Decoupled Objects](https://mlsanity.com/paper/2401.13203/) (2024)
- [DreamScene: 3D Gaussian-based End-to-end Text-to-3D Scene Generation](https://mlsanity.com/paper/2507.13985/) (2025)
- [GeoTexBuild: 3D Building Model Generation from Map Footprints](https://mlsanity.com/paper/2504.08419/) (2025)
- [DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion](https://mlsanity.com/paper/2605.16807/) (2026)

## Abstract (arXiv)

We propose Text2Scene, a method to automatically create realistic textures for virtual scenes composed of multiple objects. Guided by a reference image and text descriptions, our pipeline adds detailed texture on labeled 3D geometries in the room such that the generated colors respect the hierarchical structure or semantic parts that are often composed of similar materials. Instead of applying flat stylization on the entire scene at a single step, we obtain weak semantic cues from geometric segmentation, which are further clarified by assigning initial colors to segmented parts. Then we add texture details for individual objects such that their projections on image space exhibit feature embedding aligned with the embedding of the input. The decomposition makes the entire pipeline tractable to a moderate amount of computation resources and memory. As our framework utilizes the existing resources of image and text embedding, it does not require dedicated datasets with high-quality textures designed by skillful artists. To the best of our knowledge, it is the first practical and scalable approach that can create detailed and realistic textures of the desired style that maintain structural context for scenes with multiple objects.