# CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling

arXiv: https://arxiv.org/abs/2604.27361 · HTML: https://mlsanity.com/paper/2604.27361/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 63 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Builds on (most cited first, 30 of 37)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2302.04867/) (2023)
- [3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics](https://mlsanity.com/paper/2011.09127/) (2020)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [ATISS: Autoregressive Transformers for Indoor Scene Synthesis](https://mlsanity.com/paper/2110.03675/) (2021)
- [SceneFormer: Indoor Scene Generation with Transformers](https://mlsanity.com/paper/2012.09793/) (2020)
- [InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior](https://mlsanity.com/paper/2402.04717/) (2024)
- [Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models](https://mlsanity.com/paper/1811.12463/) (2018)
- [I-Design: Personalized LLM Interior Designer](https://mlsanity.com/paper/2404.02838/) (2024)
- [Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphs](https://mlsanity.com/paper/2108.08841/) (2021)
- [Constrained Graphic Layout Generation via Latent Optimization](https://mlsanity.com/paper/2108.00871/) (2021)
- [LEGO-Net: Learning Regular Rearrangements of Objects in Rooms](https://mlsanity.com/paper/2301.09629/) (2023)
- [EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion](https://mlsanity.com/paper/2405.00915/) (2024)
- [MIME: Human-Aware 3D Scene Generation](https://mlsanity.com/paper/2212.04360/) (2022)
- [Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases](https://mlsanity.com/paper/2403.09675/) (2024)
- [SceneTeller: Language-to-3D Scene Generation](https://mlsanity.com/paper/2407.20727/) (2024)
- [SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometry](https://mlsanity.com/paper/2302.10237/) (2023)
- [GRAINS: Generative Recursive Autoencoders for INdoor Scenes](https://mlsanity.com/paper/1807.09193/) (2018)
- [Mixed Diffusion for 3D Indoor Scene Synthesis](https://mlsanity.com/paper/2405.21066/) (2024)
- [Global-Local Tree Search in VLMs for 3D Indoor Scene Generation](https://mlsanity.com/paper/2503.18476/) (2025)
- [FlairGPT: Repurposing LLMs for Interior Designs](https://mlsanity.com/paper/2501.04648/) (2025)
- [Chat2Layout: Interactive 3D Furniture Layout with a Multimodal LLM](https://mlsanity.com/paper/2407.21333/) (2024)
- [LayoutEnhancer: Generating Good Indoor Layouts from Imperfect Data](https://mlsanity.com/paper/2202.00185/) (2022)
- [DeBaRA: Denoising-Based 3D Room Arrangement Generation](https://mlsanity.com/paper/2409.18336/) (2024)
- [Advances in Data-Driven Analysis and Synthesis of 3D Indoor Scenes](https://mlsanity.com/paper/2304.03188/) (2023)
- [Fast and Scalable Position-Based Layout Synthesis](https://mlsanity.com/paper/1809.10526/) (2018)
- [COFS: Controllable Furniture layout Synthesis](https://mlsanity.com/paper/2205.14657/) (2022)

## Built on by (most cited first, 1 of 1)

- [Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstruction](https://mlsanity.com/paper/2609.23796/) (2026)

## Abstract (arXiv)

Synthesizing realistic 3D indoor scenes remains challenging due to data scarcity and the difficulty of simultaneously enforcing global architectural constraints and local semantic consistency. Existing approaches often overlook structural boundaries or rely on fully connected relation graphs that introduce redundant generation errors. Inspired by human design cognition, we present CasLayout, a cascaded diffusion framework that decomposes the joint scene generation task into four conditional sub-stages with explicit physical and semantic roles: (1) predicting furniture quantity and categories, (2) refining object sizes and feature embeddings, (3) modeling spatial relationships in a latent space, and (4) generating Oriented Bounding Boxes (OBBs). This decoupled architecture reduces data requirements and enables flexible integration of Large Language Models (LLMs) and Vision Language Models (VLMs) for zero-shot tasks such as image-to-scene generation. To maintain physical validity within complex floor plans, we explicitly model building elements (e.g., walls, doors, and windows) as conditional constraints. Furthermore, to address the high entropy of dense relation graphs, we introduce a sparse relation graph formulation aligned with human spatial descriptions. By encoding these sparse graphs into a compact latent space using a bidirectional Variational Autoencoder (VAE), the proposed framework provides enhanced relational controllability, allowing generated layouts to better respect functional organization. Experiments demonstrate that CasLayout achieves state-of-the-art performance in fidelity and diversity while enabling improved controllability in practical applications.