3D Scene Generation

Ask about this topic

Overview

3D scene generation studies how to turn prompts and visual observations into environments with coherent layouts, geometry, appearance, and sometimes motion or interaction. Methods range from procedural rules and language-model agents to diffusion, flow-matching, and autoregressive models that generate meshes, Gaussian splats, voxels, or occupancy representations. Work targets indoor design, large-scale worlds, driving scenes, and simulation for robotics, using constraints, rendering feedback, and physics checks to improve control and usability. A central challenge is balancing visual realism and scalable generation with consistent geometry, physical plausibility, editability, and reliable evaluation.

Latest papers

CardsList

191 papers25 papers in the last four weeks, up 39% on the four weeks before. 0.1% of all new papers.

  1. StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics

    Apr 1, 2026Bingliang Li, Zhenhong Sun, Jiaming Bian +63D Scene Generation3D Scene Layout Generation

    Independent Researcher · Australia National University Australia · Central South University China +4

  2. Extend3D: Town-Scale 3D Generation

    Mar 31, 2026Seungwoo Yoon, Jinmo Kim, Jaesik ParkImage-to-3D Scene Generation3D Scene Generation

    Seoul National University

  3. WorldFlow3D: Flowing Through 3D Distributions for Unbounded World Generation

    Mar 31, 2026Amogh Joshi, Julian Ost, Felix Heide3D Scene Generation3D Scene Layout Generation

    Princeton University · Torc Robotics

  4. Stepper: Stepwise Immersive Scene Generation with Multiview Panoramas

    Mar 30, 2026Felix Wimbauer, Fabian Manhardt, Michael Oechsle +43D Scene GenerationText-to-3D Generation

    Google · MCML · Technical University of Munich +1

  5. SonoWorld: From One Image to a 3D Audio-Visual Scene

    Mar 30, 2026Derong Jin, Xiyi Chen, Ming C. Lin +1Audio-Video Generation3D Scene Generation

    University of Maryland, College Park

  6. Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow

    Mar 30, 2026Quan Meng, Yujin Chen, Lei Li +23D Scene Completion3D Scene Generation

    Technical University of Munich · University of Virginia

  7. GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation

    Mar 27, 2026Nicolas von Lützow, Barbara Rössle, Katharina Schmid +13D Gaussian Splatting3D Scene Generation

    Technical University of Munich, Germany

  8. AeroScene: Progressive Scene Synthesis for Aerial Robotics

    Mar 24, 2026Nghia Vu, Tuong Do, Dzung Tran +63D Scene GenerationSynthetic Data Generation for Robotics

    AIOZ Ltd., Singapore · University of Liverpool, UK · National Tsing Hua University, Taiwan +2

  9. WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion

    Mar 24, 2026Manuel-Andreas Schneider, Angela Dai3D Scene Generation3D Scene Representation

    Technical University of Munich, Germany

  10. WorldAgents: Can Foundation Image Models be Agents for 3D World Models?

    Mar 20, 2026Ziya Erkoç, Angela Dai, Matthias NießnerProcedural 3D Generation3D Scene Generation

    Technical University of Munich

  11. FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow

    Mar 20, 2026Zhifei Yang, Guangyao Zhai, Keyang Lu +6Image-to-3D Scene GenerationIndoor Scene Generation

    School of Computer Science, Peking University · Technical University of Munich · Beijing Jiaotong University +3

  12. Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors

    Mar 19, 2026Jiatong Xia, Zicheng Duan, Anton van den Hengel +13D Asset Generation3D Shape Generation

    Australian Institute for Machine Learning, University of Adelaide, Australia

  13. World Reconstruction From Inconsistent Views

    Mar 17, 2026Lukas Höllein, Matthias Nießner3D Reconstruction3D Scene Generation

    Technical University of Munich, Germany

  14. OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder

    Mar 17, 2026Sensen Gao, Zhaoqing Wang, Qihang Cao +53D Scene Generation3D Diffusion Models

    Mohamed bin Zayed University of Artificial Intelligence · AISphere · Shanghai Jiao Tong University +3

  15. Interact3D: Compositional 3D Generation of Interactive Objects

    Mar 17, 2026Hui Shan, Keyang Luo, Ming Li +43D Asset Generation3D Scene Generation

    Zhejiang University, China · Shanghai Innovation Institute, China · Westlake University, China +4

  16. Grounding World Simulation Models in a Real-World Metropolis

    Mar 16, 2026Junyoung Seo, Hyunwook Choi, Minkyung Kwon +10Retrieval-Augmented Video GenerationVideo World Models

    KAIST AI · NAVER AI Lab · SNU AIIS

  17. Scene Generation at Absolute Scale: Utilizing Semantic and Geometric Guidance From Text for Accurate and Interpretable 3D Indoor Scene Generation

    Mar 14, 2026Stefan Ainetter, Thomas Deixelberger, Edoardo A. Dominici +3Diffusion Model Guidance3D Scene Generation

    Huawei Technologies, Austria · Graz University of Technology, Austria · Huawei Technologies, Switzerland

  18. SceneAssistant: A Visual Feedback Agent for Open-Vocabulary 3D Scene Generation

    Mar 12, 2026Jun Luo, Jiaxiang Tang, Ruijie Lu +13D Scene GenerationText-to-3D Generation

    Peking University · NVIDIA

  19. MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generation

    Mar 12, 2026Baicheng Li, Dong Wu, Jun Li +43D Shape Generation3D Scene Generation

    Peking University · JD Explore Academy

  20. MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks

    Mar 12, 2026Lirong Che, Shuo Wen, Shan Huang +53D Scene GenerationIndoor Scene Generation

    Tsinghua University · AgiBot · McGill University, MILA - Quebec AI Institute

  21. PARSE: Part-Aware Relational Spatial Modeling

    Mar 8, 2026Yinuo Bai, Peijun Xu, Kuixiang Shao +5Spatial Reasoning3D Spatial Reasoning

    ShanghaiTech University · Deemos Technology

  22. Pano3DComposer: Feed-Forward Compositional 3D Scene Generation from Single Panoramic Image

    Mar 6, 2026Zidian Qiu, Ancong Wu3D Scene GenerationImage-to-3D Scene Generation

    Sun Yat-sen University

  23. Cog2Gen3D: Sculpturing 3D Semantic-Geometric Cognition for 3D Generation

    Mar 6, 2026Haonan Wang, Hanyu Zhou, Haoyue Liu +23D Scene Generation3D Diffusion Models

    School of Artificial and Automation, Huazhong University of Science and Technology · School of Computing, National University of Singapore · School of Computing, Macquarie University

  24. DM-CFO: A Diffusion Model for Compositional 3D Tooth Generation with Collision-Free Optimization

    Mar 4, 2026Yan Tian, Pengcheng Xue, Weiping Ding +5Part-Level 3D Generation3D Diffusion Models

    School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou 310018, China · Shining3D Tech Co., Ltd., Hangzhou 311200, China · School of Artificial Intelligence and Computer Science, Nantong University, Nantong 226019, China +8

  25. Beyond Pixel Histories: World Models with Persistent 3D State

    Mar 3, 2026Samuel Garcin, Thomas Walker, Steven McDonagh +5World ModelsInteractive World Models

    University of Edinburgh · Microsoft Research

  26. TIMI: Training-Free Image-to-3D Multi-Instance Generation with Spatial Fidelity

    Mar 2, 2026Xiao Cai, Pengpeng Zeng, Ji Zhang +33D Scene Generation3D Diffusion Models

    School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China · School of Computer Science and Technology, Tongji University, Shanghai, China · School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China +1

  27. SceneTransporter: Optimal Transport-Guided Compositional Latent Diffusion for Single-Image Structured 3D Scene Generation

    Feb 26, 2026Ling Wang, Hao-Xiang Guo, Xinzhou Wang +93D Scene GenerationImage-to-3D Scene Generation

    Xi’an Research Institute of Hi-Tech · Tsinghua University · SkyWork AI +3

  28. One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Image

    Feb 23, 2026Pengfei Wang, Liyi Chen, Zhiyuan Ma +33D Scene GenerationImage-to-3D Scene Generation

    The Hong Kong Polytechnic University

  29. SceneTok: A Compressed, Diffusable Token Space for 3D Scenes

    Feb 21, 2026Mohammad Asim, Christopher Wewer, Jan Eric Lenssen3D Scene Representation3D Scene Generation

    Max Planck Institute for Informatics, Saarland Informatics Campus

  30. RoboLayout: Differentiable 3D Scene Generation for Embodied Agents

    Feb 18, 2026Ali Shamsaddinlou3D Scene Layout Generation3D Scene Generation