# Disentangled 3D Scene Generation with Layout Learning

arXiv: https://arxiv.org/abs/2402.16936 · HTML: https://mlsanity.com/paper/2402.16936/

## Key facts

- Cited by 33 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 26 Feb 2024.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [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)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation](https://mlsanity.com/paper/2212.00774/) (2022)
- [Zero-Shot Text-Guided Object Generation with Dream Fields](https://mlsanity.com/paper/2112.01455/) (2021)
- [Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation](https://mlsanity.com/paper/2312.02145/) (2023)
- [ReconFusion: 3D Reconstruction with Diffusion Priors](https://mlsanity.com/paper/2312.02981/) (2023)
- [Diffusion Self-Guidance for Controllable Image Generation](https://mlsanity.com/paper/2306.00986/) (2023)
- [Holodeck: Language Guided Generation of 3D Embodied AI Environments](https://mlsanity.com/paper/2312.09067/) (2023)
- [Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence](https://mlsanity.com/paper/2305.14334/) (2023)

## Built on by (most cited first, 30 of 33)

- [CAT3D: Create Anything in 3D with Multi-View Diffusion Models](https://mlsanity.com/paper/2405.10314/) (2024)
- [LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models](https://mlsanity.com/paper/2412.02193/) (2024)
- [TC4D: Trajectory-Conditioned Text-to-4D Generation](https://mlsanity.com/paper/2403.17920/) (2024)
- [PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models](https://mlsanity.com/paper/2412.18608/) (2024)
- [ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance](https://mlsanity.com/paper/2403.12409/) (2024)
- [REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment](https://mlsanity.com/paper/2405.18525/) (2024)
- [WonderTurbo: Generating Interactive 3D World in 0.72 Seconds](https://mlsanity.com/paper/2504.02261/) (2025)
- [Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane](https://mlsanity.com/paper/2403.16210/) (2024)
- [3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting](https://mlsanity.com/paper/2405.18424/) (2024)
- [AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation](https://mlsanity.com/paper/2410.07164/) (2024)
- [3D Scene Generation: A Survey](https://mlsanity.com/paper/2505.05474/) (2025)
- [Sketch2Scene: Automatic Generation of Interactive 3D Game Scenes from User's Casual Sketches](https://mlsanity.com/paper/2408.04567/) (2024)
- [WorldCraft: Photo-Realistic 3D World Creation and Customization via LLM Agents](https://mlsanity.com/paper/2502.15601/) (2025)
- [BrightDreamer: Generic 3D Gaussian Generative Framework for Fast Text-to-3D Synthesis](https://mlsanity.com/paper/2403.11273/) (2024)
- [PhyCAGE: Physically Plausible Compositional 3D Asset Generation from a Single Image](https://mlsanity.com/paper/2411.18548/) (2024)
- [MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generation](https://mlsanity.com/paper/2502.05874/) (2025)
- [Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion](https://mlsanity.com/paper/2507.04403/) (2025)
- [Agentic 3D Scene Generation with Spatially Contextualized VLMs](https://mlsanity.com/paper/2505.20129/) (2025)
- [Semantic Score Distillation Sampling for Compositional Text-to-3D Generation](https://mlsanity.com/paper/2410.09009/) (2024)
- [DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priors](https://mlsanity.com/paper/2407.16260/) (2024)
- [Scene123: One Prompt to 3D Scene Generation via Video-Assisted and Consistency-Enhanced MAE](https://mlsanity.com/paper/2408.05477/) (2024)
- [Towards Geometric and Textural Consistency 3D Scene Generation via Single Image-guided Model Generation and Layout Optimization](https://mlsanity.com/paper/2507.14841/) (2025)
- [DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer](https://mlsanity.com/paper/2409.08271/) (2024)
- [FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow](https://mlsanity.com/paper/2603.19598/) (2026)
- [3D-Generalist: Self-Improving Vision-Language-Action Models for Crafting 3D Worlds](https://mlsanity.com/paper/2507.06484/) (2025)
- [Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image](https://mlsanity.com/paper/2606.24138/) (2026)
- [DreamAnywhere: Object-Centric Panoramic 3D Scene Generation](https://mlsanity.com/paper/2506.20367/) (2025)
- [Seeing Through Clutter: Structured 3D Scene Reconstruction via Iterative Object Removal](https://mlsanity.com/paper/2602.04053/) (2026)
- [RoamScene3D: Immersive Text-to-3D Scene Generation via Adaptive Object-aware Roaming](https://mlsanity.com/paper/2601.19433/) (2026)
- [HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language Models](https://mlsanity.com/paper/2604.10772/) (2026)

## Abstract (arXiv)

We introduce a method to generate 3D scenes that are disentangled into their component objects. This disentanglement is unsupervised, relying only on the knowledge of a large pretrained text-to-image model. Our key insight is that objects can be discovered by finding parts of a 3D scene that, when rearranged spatially, still produce valid configurations of the same scene. Concretely, our method jointly optimizes multiple NeRFs from scratch - each representing its own object - along with a set of layouts that composite these objects into scenes. We then encourage these composited scenes to be in-distribution according to the image generator. We show that despite its simplicity, our approach successfully generates 3D scenes decomposed into individual objects, enabling new capabilities in text-to-3D content creation. For results and an interactive demo, see our project page at https://dave.ml/layoutlearning/