# SceneTransporter: Optimal Transport-Guided Compositional Latent Diffusion for Single-Image Structured 3D Scene Generation arXiv: https://arxiv.org/abs/2602.22785 ยท HTML: https://mlsanity.com/paper/2602.22785/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. - Builds on 47 of its 48 references that are in the map. - First posted on arXiv 26 Feb 2026. ## Placed in - Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/) ## Builds on (most cited first, 30 of 47) - [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022) - [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022) - [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (2022) - [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024) - [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023) - [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023) - [Zero-shot Image-to-Image Translation](https://mlsanity.com/paper/2302.03027/) (2023) - [FateZero: Fusing Attentions for Zero-shot Text-based Video Editing](https://mlsanity.com/paper/2303.09535/) (2023) - [3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models](https://mlsanity.com/paper/2301.11445/) (2023) - [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025) - [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023) - [Video-P2P: Video Editing with Cross-attention Control](https://mlsanity.com/paper/2303.04761/) (2023) - [Training-Free Layout Control with Cross-Attention Guidance](https://mlsanity.com/paper/2304.03373/) (2023) - [ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding](https://mlsanity.com/paper/2212.05171/) (2022) - [Uni3D: Exploring Unified 3D Representation at Scale](https://mlsanity.com/paper/2310.06773/) (2023) - [Style Aligned Image Generation via Shared Attention](https://mlsanity.com/paper/2312.02133/) (2023) - [TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models](https://mlsanity.com/paper/2502.06608/) (2025) - [ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding](https://mlsanity.com/paper/2305.08275/) (2023) - [XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies](https://mlsanity.com/paper/2312.03806/) (2023) - [Localizing Object-level Shape Variations with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.11306/) (2023) - [DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion](https://mlsanity.com/paper/2411.04928/) (2024) - [MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation](https://mlsanity.com/paper/2412.03558/) (2024) - [Wonderland: Navigating 3D Scenes from a Single Image](https://mlsanity.com/paper/2412.12091/) (2024) - [Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries](https://mlsanity.com/paper/2409.12640/) (2024) - [PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers](https://mlsanity.com/paper/2506.05573/) (2025) - [BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation](https://mlsanity.com/paper/2401.17053/) (2024) - [DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting](https://mlsanity.com/paper/2404.06903/) (2024) - [Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing](https://mlsanity.com/paper/2309.15664/) (2023) - [DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation](https://mlsanity.com/paper/2412.18597/) (2024) - [DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling](https://mlsanity.com/paper/2404.03575/) (2024) ## Built on by (most cited first, 6 of 6) - [WorldClaw: Agentic 3D Open-World Generation at Scale](https://mlsanity.com/paper/2608.05248/) (2026) - [One Video, One World: Turning Monocular Video into Physical 4D Scenes](https://mlsanity.com/paper/2606.31388/) (2026) - [SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration](https://mlsanity.com/paper/2606.08402/) (2026) - [GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning](https://mlsanity.com/paper/2609.05927/) (2026) - [ISAP-3D: Identity-Slot Aligned Part-Aware 3D Generation](https://mlsanity.com/paper/2606.12099/) (2026) - [Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstruction](https://mlsanity.com/paper/2609.23796/) (2026) ## Abstract (arXiv) We introduce SceneTransporter, an end-to-end framework for structured 3D scene generation from a single image. While existing methods generate part-level 3D objects, they often fail to organize these parts into distinct instances in open-world scenes. Through a debiased clustering probe, we reveal a critical insight: this failure stems from the lack of structural constraints within the model's internal assignment mechanism. Based on this finding, we reframe the task of structured 3D scene generation as a global correlation assignment problem. To solve this, SceneTransporter formulates and solves an entropic Optimal Transport (OT) objective within the denoising loop of the compositional DiT model. This formulation imposes two powerful structural constraints. First, the resulting transport plan gates cross-attention to enforce an exclusive, one-to-one routing of image patches to part-level 3D latents, preventing entanglement. Second, the competitive nature of the transport encourages the grouping of similar patches, a process that is further regularized by an edge-based cost, to form coherent objects and prevent fragmentation. Extensive experiments show that SceneTransporter outperforms existing methods on open-world scene generation, significantly improving instance-level coherence and geometric fidelity. Code and models will be publicly available at https://2019epwl.github.io/SceneTransporter/.