Author Contributions · Spatial Intelligence Handbook

Contributions are listed in the order of the author list on the title page. For each author who drafted text, the parts of the handbook they wrote are given in book order, and a co-authored part names its co-author. Authors who reviewed the manuscript and advised on its direction are marked as such.

•
Shengqiong Wu, University of Oxford:
- –
  
  Part I, Introduction and Background, Chapters 1–3 (with Hao Fei)
- –
  
  Audio, Section 4.5
- –
  
  Object Tracking, Section 6.4.2
- –
  
  Physical Reasoning, Section 7.1.2
- –
  
  Differentiable Optimization Layers for Spatial Reasoning, Section 7.2.4
- –
  
  Reinforcement Learning with Spatial Inductive Biases, Section 7.2.5
- –
  
  Hybrid Spatial Reasoning, Section 7.4
- –
  
  Spatial Reasoning Benchmarks, Section 7.5
- –
  
  3D Object Synthesis, Section 8.2.1
- –
  
  3D Scene Reconstruction, Section 8.2.3
- –
  
  3D Scene Editing, Section 8.2.5
- –
  
  Summary, Challenges, and Future Directions of Video Spatial Generation, Section 8.3.6
- –
  
  Introduction to Motion Generation, Section 8.4
- –
  
  Programmatic and Symbolic Spatial Generation, Section 8.7
- –
  
  Summary and Outlook of Spatial Generation, Section 8.8
- –
  
  Aerospace Engineering, Section 11.3
- –
  
  Spatial Intelligence for Others, Chapter 14
- –
  
  Part V, Discussions and Futures, Chapters 15–17
- –
  
  Introductions to Parts II–IV, to Chapters 4 and 6–14, and to the sections of Chapters 6–8
•
Yu Zhao, National University of Singapore:
- –
  
  Height and Distance Estimation, Section 6.2.3
- –
  
  Layout Estimation and Room Parsing, Section 6.3.3
- –
  
  Mapping and SLAM, Section 6.3.5
- –
  
  Surface Normal Estimation, Section 6.2.2
- –
  
  Visual Odometry and Camera Pose Estimation, Section 6.2.4
- –
  
  Scene Flow Estimation, Section 6.4.1
- –
  
  Motion Generation, Sections 8.4.1–8.4.4
- –
  
  Autonomous Driving, Section 9.2
- –
  
  GeoAI, Section 11.2
•
Tianjie Ju, National University of Singapore:
- –
  
  Foundations: What Spatial Intelligence Requires, Chapter 15
- –
  
  Research Gaps and Future Directions, Chapter 16
- –
  
  Content Screening
•
Jundong Xu, National University of Singapore:
- –
  
  Geometric and Algebraic Reasoning, Section 7.1.1
- –
  
  Topological and Graph-based Reasoning, Section 7.1.3
- –
  
  Constraint-based Spatial Solving, Section 7.1.4
- –
  
  Rule-based and Programmatic Reasoning, Section 7.1.5
- –
  
  Causal Reasoning, Section 7.1.6
- –
  
  Warehouse and Industrial Logistics, Section 9.5
•
Bobo Li, National University of Singapore:
- –
  
  Temporal Localization, Section 6.4.3
- –
  
  Multi-agent Spatial Reasoning, Section 7.2.6
- –
  
  Text-to-image Generation, Section 8.1.1
- –
  
  Entertainment, Section 10.2
- –
  
  AR/VR/XR, Section 10.1 (with Xin Kong)
•
Jingkang Yang and Shulin Tian, Nanyang Technological University, Singapore:
- –
  
  Chain-of-Thought for Spatial Reasoning, Section 7.3.3
- –
  
  Tool-augmented Reasoning, Section 7.3.5
- –
  
  Retrieval- & Memory-augmented Spatial Reasoning, Section 7.3.6
- –
  
  Agentic Spatial Reasoning, Section 7.3.7
- –
  
  Assistant, Section 13.1
•
Daoan Zhang, University of Rochester:
- –
  
  Audio-Visual Spatial Localization, Section 6.5.1
- –
  
  2D Spatial-aware Image Generation, Section 8.1.2
- –
  
  2D Spatial Inpainting & Editing, Section 8.1.3
- –
  
  Medicine and Clinical Healthcare, Section 12.1
•
Yanguang Zhao, National University of Singapore:
- –
  
  Keypoint and Landmark Detection, Section 6.1.3
- –
  
  Depth Estimation, Section 6.2.1
- –
  
  Natural Science, Section 12.2
•
Xuan Ju, The Chinese University of Hong Kong:
- –
  
  Text-to-Video Generation, Section 8.3.1
- –
  
  Spatial Controlled Video Generation, Section 8.3.2
- –
  
  Temporal Controlled Video Generation, Section 8.3.3
- –
  
  Other Controlled Video Generation, Section 8.3.4
- –
  
  Video Editing, Section 8.3.5
•
Haoyu Zhao, The Chinese University of Hong Kong:
- –
  
  3D Representations, Section 4.2
- –
  
  4D Spatial Generation, Section 8.5
•
Yuchen Zhou, National University of Singapore:
- –
  
  Spatial Relation Extraction, Section 6.3.1
- –
  
  Scene Graph Generation, Section 6.3.2
- –
  
  Action Detection, Section 6.3.4
- –
  
  LLM/VLM-centric Spatial Reasoning, Section 7.3.1
- –
  
  VLA-based Spatial Reasoning, Section 7.3.2
•
Xiangtai Li, Nanyang Technological University, Singapore:
- –
  
  2D Representations, Section 4.1
- –
  
  Object Detection, Section 6.1.1
- –
  
  Segmentation, Section 6.1.2
•
Zhedong Zheng, University of Macau:
- –
  
  Aerial Agents, Section 9.4
•
Joy Hsu, Stanford University:
- –
  
  Domain-Specific Representations, Section 4.6
- –
  
  Cross-Modal Spatial Representation, Chapter 5
•
Xin Kong, Imperial College London:
- –
  
  4D Representations, Section 4.3 (with Chuanxia Zheng)
- –
  
  3D Scene Synthesis, Section 8.2.2
- –
  
  AR/VR/XR, Section 10.1 (with Bettina Schlager)
•
Ruining Li, University of Oxford:
- –
  
  World-Model-based Spatial Reasoning, Section 7.3.8 (with Hao Fei)
- –
  
  Digital Twins, Section 11.1
•
Cheng Zhang, Monash University:
- –
  
  3D Panorama Synthesis, Section 8.2.4
•
Chengzu Li, University of Cambridge:
- –
  
  Scene Classification, Section 6.1.4 (with Hao Fei)
- –
  
  Implicit Neural Spatial Reasoning, Section 7.2.1 (with Hao Fei)
- –
  
  Explicit Structured Neural Reasoning, Section 7.2.2 (with Hao Fei)
- –
  
  Geometry-aware Neural Spatial Reasoning, Section 7.2.3 (with Hao Fei)
- –
  
  Code/DSL Generation for Spatial Reasoning, Section 7.3.4 (with Hao Fei)
•
Jiafei Duan, National University of Singapore:
- –
  
  Robotic Manipulation, Section 9.1
•
Yu (Bryan) Zhou, University of California, Los Angeles:
- –
  
  Vision-Language Grounding, Section 6.5.2
•
Kenneth Li, Harvard University:
- –
  
  Language Representations, Section 4.4
•
Chuanxia Zheng, Nanyang Technological University, Singapore:
- –
  
  4D Representations, Section 4.3 (with Xin Kong)
•

Lei Cui, Microsoft Research: Reviewing & Advisory, providing comments and feedback that shaped the direction of the handbook
•

Furu Wei, Microsoft Research: Reviewing & Advisory, providing comments and feedback that shaped the direction of the handbook
•

Ziwei Liu, Nanyang Technological University, Singapore: Reviewing & Advisory, providing comments and feedback that shaped the direction of the handbook
•

Steven K. Feiner, Columbia University: Reviewing & Advisory, providing comments and feedback that shaped the direction of the handbook
•

Jiebo Luo, University of Rochester: Reviewing & Advisory, providing comments and feedback that shaped the direction of the handbook
•

Jianfei Cai, Monash University: Reviewing & Advisory, providing comments and feedback that shaped the direction of the handbook
•

Shuicheng Yan, National University of Singapore: Reviewing & Advisory, providing comments and feedback that shaped the direction of the handbook
•

Ming-Hsuan Yang, University of California, Merced: Reviewing & Advisory, providing comments and feedback that shaped the direction of the handbook
•
Hao Fei, University of Oxford:
- –
  
  Part I, Introduction and Background, Chapters 1–3 (with Shengqiong Wu)
- –
  
  Scene Classification, Section 6.1.4 (with Chengzu Li)
- –
  
  Pose Estimation, Section 6.2.5
- –
  
  Implicit Neural Spatial Reasoning, Section 7.2.1 (with Chengzu Li)
- –
  
  Explicit Structured Neural Reasoning, Section 7.2.2 (with Chengzu Li)
- –
  
  Geometry-aware Neural Spatial Reasoning, Section 7.2.3 (with Chengzu Li)
- –
  
  Code/DSL Generation for Spatial Reasoning, Section 7.3.4 (with Chengzu Li)
- –
  
  World-Model-based Spatial Reasoning, Section 7.3.8 (with Ruining Li)
- –
  
  World Modeling, Section 8.6
- –
  
  Wearable AI System, Section 9.3
- –
  
  Figures: drew part of the handbook’s illustrations, most notably the teaser figure