Spatial intelligence
Perception systems for understanding real-world spaces in 3D and 4D, with emphasis on semantic scene understanding and geometric reasoning.
Stanford University
Designing adaptive spaces with computer vision, generative AI, and mixed reality.
I lead the Gradient Spaces group, researching at the intersection of Computer Vision, Generative AI, and the built environment. My work focuses on developing machine perception architectures and applications capable of designing, reconstructing, and predicting in adaptive physical and digital spaces.
Research at the intersection of computer vision, generative AI, and the built environment.
About
Building intelligent systems for the spaces people inhabit.
My area of focus is on developing quantitative and data-driven methods that learn from real-world visual data to generate, predict, and simulate new or renewed built environments that place the human in the center.
My goal is to create sustainable, inclusive, and adaptive built environments that can support our current and future physical and digital needs.
I am intrigued by the idea of creating responsive spaces that blend from the 100% physical (real reality) to the 100% digital (virtual reality) and anything in between, with the use of Mixed Reality.
Read more in A Day in the Life of an Architect in the Gradient World.
Current focus
- • Machine perception for built environments
- • Generative AI for design and simulation
- • Mixed reality and adaptive spaces
- • Sustainable, inclusive spatial intelligence
Education & awards
Background and recognition
Education
- Postdoctoral Researcher (2023), ETH Zurich, DBAUG and DINFK, w/ Prof. Daniel Hall, Prof. Catherine de Wolf, and Prof. Marc Pollefeys
- Ph.D. (2020), Civil and Environmental Engineering with Minor in Computer Science, Stanford University, w/ Prof. Martin Fischer and Prof. Silvio Savarese
- MSc (2013), Computer Science, Ionian University
- MEng (2011), Architectural Engineering, University of Tokyo
- Diploma (2009), Architectural Engineering, National Technical University of Athens
- Worked as an architect and consultant for both the private and public sector.
Awards
- U. V. Helava Award - Best Paper 2025, ISPRS Journal of Photogrammetry and Remote Sensing journal-wide award for best paper in 2025
- 2026 BuiltWorlds Maverick Award on Influence and Education, Professional recognition for achievements in influence and education in the AEC industry from BuiltWorlds
- NVIDIA Academic Grant Program (Jan-Jun 2026), World-wide academic computing grant for research on "Multi-agent Video World Models"
- Google Research Scholar Program (2025-26), World-wide early-career faculty funding for research on Machine Perception
- ETH Zurich Postdoctoral Fellowship (2020-22), University-level funding for postdoctoral studies on Machine Perception for Architecture, Construction, and Facility Management
- Google Ph.D. Fellowship (2017-20), Competitive funding across North America and Europe, for Ph.D. studies on Machine Perception
- Stanford CIFE Seed Research Award (2016-17), Department-level funding, for research on "Automated Semantic Understanding of Buildings"
- Japanese Government Scholarship (MEXT) (2009-11), Competitive nation-level funding for MEng degree
Research
Lab themes
Generative design
Learning models that synthesize and predict spaces, support planning, and reason over future built conditions.
Adaptive environments
Designing responsive, data-driven physical and digital spaces that support sustainability, resilience, and human-centered use.
Publications
Academic publications
Current-year publications
FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
Kevin Qu, Tao Sun, Massimiliano Viola, Liyuan Zhu, Zhizhuo Zhou, Sayan Deb Sarkar, Konrad Schindler, Iro Armeni
arXiv preprint 2026
World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video
Liyuan Zhu, Shengyu Huang, Amrita Mazumdar, Tianye Li, Zan Gojcic, Gordon Wetzstein, Iro Armeni, Shalini De Mello, Alex Trevithick
NeurIPS 2026
GraphWrit3R: End-to-End Writing of Scene Graphs for Multi-Modal 3D Scenes
Luka Milivojevic, Nikola Popovic, Sayan Deb Sarkar, Sebastian Koch, Iro Armeni, Luc Van Gool, Danda Pani Paudel
NeurIPS 2026
CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling
Sayan Deb Sarkar, Rémi Pautrat, Ondrej Miksik, Marc Pollefeys, Iro Armeni, Mahdi Rad, Mihai Dusmanu
NeurIPS 2026
Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis
Zhengfei Kuang, Adam Sun, Liyuan Zhu, Tong Wu, Shengqu Cai, Jonathan Tremblay, Iro Armeni, Ehsan Adeli, Lior Yariv, Gordon Wetzstein
NeurIPS 2026
Energy-based Compositional Diffusion Planning
Tao Sun, Utkarsh A. Mishra, Jiaxin Lu, Danfei Xu, Iro Armeni
ICML 2026
Leveraging vision and language models to capture residential seismic vulnerabilities in the building inventory
Mia Lochhead, Iro Armeni, and Gregory Deierlein
NCEE 2026
Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching
Yue Pan, Tao Sun, Liyuan Zhu, Lucas Nunes, Iro Armeni, Jens Behley, Cyrill Stachniss
ECCV 2026 [Oral, Best Paper Candidate Award]
ReScene4D: Temporally Consistent Semantic Instance Segmentation of Evolving Indoor 3D Scenes
Emily Steiner, Jianhao Zheng, Henry Howard-Jenkins, Chris Xie, Iro Armeni
CVPR 2026
GaussFusion: Improving 3D Reconstruction in the Wild with Geometry-Informed Video Generators
Liyuan Zhu, Manjunath Narayana, Michal Stary, Will Hutchcroft, Gordon Wetzstein, Iro Armeni
CVPR 2026
WildPose: A Unified Framework for Robust Pose Estimation in the Wild
Jianhao Zheng, Liyuan Zhu, Zihan Zhu, Iro Armeni
CVPR 2026
Urban-scale Facade Material Mapping from Street View Images Using Vision–Language Models for Circular Construction Planning
Deepika Raghu, Iro Armeni, Catherine De Wolf
Scientific Reports Vol. 16, 2026
Deep Sketch-Based 3D Modeling: A Survey
Alberto Tono, Jiajun Wu, Gordon Wetzstein, Iro Armeni, Hariharan Subramonyam, James Landay, and Martin Fischer
Computer Graphics Forum 2026
Do 3D Large Language Models Really Understand 3D Spatial Relationships?
Xianzheng Ma, Tao Sun, Shuai Chen, Yash Bhalgat Sanjay, Jindong Gu, Angel X. Chang, Iro Armeni, Iro Laina, Songyou Peng, and Victor Adrian Prisacariu
ICLR 2026
Show earlier publications
ReSpace: Text-Driven 3D Scene Synthesis and Editing with Preference Alignment
Martin JJ. Bucher, Iro Armeni
arXiv preprint 2025
SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment
Binod Singh*, Sayan Deb Sarkar*, Iro Armeni
arXiv preprint
Rectified Point Flow: Generic Point Cloud Pose Estimation
Tao Sun*, Liyuan Zhu*, Shengyu Huang, Shuran Song, Iro Armeni
NeurIPS 2025 [Spotlight]
GuideFlow3D: Optimization-guided Rectified Flow for Appearance Transfer
Sayan Deb Sarkar, Sinisa Stekovic, Vincent Lepetit, Iro Armeni
NeurIPS 2025
Facade Segmentation for Solar Photovoltaic Suitability
Ayca Duran, Christoph Waibel, Bernd Bickel, Iro Armeni, Arno Schlueter
Tackling Climate Change with Machine Learning, Workshop in NeurIPS 2025
HouseTour: A Virtual Real Estate A(I)gent
Ata Celen, Marc Pollefeys, Daniel Bela Barath, Iro Armeni
ICCV 2025
ReStyle3D: Scene-level Appearance Transfer with Semantic Correspondences
Liyuan Zhu, Shengqu Cai*, Shengyu Huang*, Gordon Wetzstein, Naji Khosravan, Iro Armeni
ACM SIGGRAPH 2025
WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments
Jianhao Zheng*, Zihan Zhu*, Valentin Bieri, Marc Pollefeys, Songyou Peng, Iro Armeni
CVPR 2025
CrossOver: Scene Cross-Modal Alignment
Sayan Deb Sarkar, Ondrej Miksik, Marc Pollefeys, Dániel Barath, Iro Armeni
CVPR 2025 [Highlight]
LoopSplat: Loop Closure by Registering 3D Gaussian Splats
Liyuan Zhu, Yue Li, Erik Sandström, Shengyu Huang, Konrad Schindler, Iro Armeni
3DV 2025 [Oral Presentation]
Multi-Hexplanes: A Lightweight Map Representation for Rendering and 3D Reconstruction
Jianhao Zheng, Gabor Valasek, Daniel Barath, Iro Armeni
WACV 2025 [Oral Presentation]
MAP-ADAPT: Real-Time Quality-Adaptive Semantic 3D Maps
Jianhao Zheng, Daniel Barath, Marc Pollefeys, Iro Armeni
ECCV 2024
"Where am I?" Scene Retrieval with Language
Jiaqi Chen, Daniel Barath, Iro Armeni, Marc Pollefeys, Hermann Blum
ECCV 2024
I-Design: Personalized LLM Interior Designer
Ata Çelen, Guo Han, Konrad Schindler, Luc Van Gool, Iro Armeni*, Anton Obukhov*, Xi Wang*
CV4Metaverse, Workshop in ECCV 2024
Nothing Stands Still: A Spatiotemporal Benchmark on 3D Point Cloud Registration Under Large Geometric and Temporal Change
Tao Sun, Yan Hao, Shengyu Huang, Silvio Savarese, Konrad Schindler, Marc Pollefeys, Iro Armeni
ISPRS Journal of Photogrammetry and Remote Sensing 2025 [Best Paper]
Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments
Liyuan Zhu, Shengyu Huang, Konrad Schindler, Iro Armeni
CVPR 2024 [Highlight]
Multiway Point Cloud Mosaicking with Diffusion and Global Optimization
Shengze Jin, Iro Armeni, Marc Pollefeys, Daniel Barath
CVPR 2024
Semantically Guided Feature Matching for Visual SLAM
Oguzhan Ilter, Iro Armeni, Marc Pollefeys, Daniel Barath
ICRA 2024
Volumetric Semantically Consistent 3D Panoptic Mapping
Yang Miao, Iro Armeni, Marc Pollefeys, Daniel Barath
IROS 2024 Oral Presentation
Q-REG: End-to-End Trainable Point Cloud Registration with Surface Curvature
Shengze Jin, Daniel Barath, Marc Pollefeys, Iro Armeni
3DV 2024
SGAligner: 3D Scene Alignment with Scene Graphs
Sayan Deb Sarkar, Ondrej Miksik, Marc Pollefeys, Daniel Barath, Iro Armeni
ICCV 2023
ARrow: A Real-Time AR Rowing Coach
Elena Iannuci, Zhu-Tian Chen, Iro Armeni, Marc Pollefeys, Hanspeter Pfister, Johanna Beyer
EuroVis 2023 [Best Short Paper Honorable Mention Award]
Learning-Based Relational Object Matching Across Views
Cathrin Elich, Iro Armeni, Martin R. Oswald, Marc Pollefeys, Joerg Stueckler
ICRA 2023
HoloLabel: Augmented Reality User-In-The-Loop Online Annotation Tool for As-Is Building Information
Dhruv Agrawal*, Janik Lobsiger*, Jessica Bo, Véronique Kaufmann, Iro Armeni
EC3 2022
SemSpray: Virtual Reality As-Is Semantic Information Labeling Tool for 3D Spatial Data
Yiming Zhao*, Cyprien Fol*, Yuchang Jiang, Tianyu Wu, Iro Armeni
EC3 2022
ImpliCity: City Modeling From Satellite Images with Deep Implicit Occupancy Fields
Corinne Stucker, Bingxin Ke, Yuanwen Yue, Shengyu Huang, Iro Armeni, Konrad Schindler
ISPRS Congress 2022 [Best Young Author Award]
Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation
Bryan Chen*, Alexander Sax*, Gene Lewis, Iro Armeni, Silvio Savarese, Amir Zamir, Jitendra Malik, Lerrel Pinto
CoRL 2020
3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera
Iro Armeni, Jerry Zhi-Yang He, JunYoung Gwak, Amir R. Zamir, Martin Fischer, Jitendra Malik, Silvio Savarese
ICCV 2019
SEGCloud: Semantic Segmentation of 3D Point Clouds
Lyne P. Tchapmi, Christopher B. Choy, Iro Armeni, JunYoung Gwak, Silvio Savarese
3DV 2017 [Spotlight Presentation]
Joint 2D-3D-Semantic Data for Indoor Scene Understanding
Iro Armeni*, Alexander Sax*, Amir R. Zamir, Silvio Savarese
Technical Report 2017
3D Semantic Parsing of Large-Scale Indoor Spaces
Iro Armeni, Ozan Sener, Amir R. Zamir, Helen Jiang, Ioannis Brilakis, Martin Fisher, Silvio Savarese
CVPR 2016 [Oral Presentation]
State of Research in Automatic As-Built Modelling
Viorica Pătrăucean, Iro Armeni, Mohammad Nahangi, Jamie Yeung, Ioannis Brilakis, Carl Haas
Advanced Engineering Informatics 2015
A dynamic identification of a historical building using accelerometers with interface modules and a digital synchronization method
Luigi Spedicato, Iro Armeni, Nicola Ivan Giannoccaro, Markos Avlonitis, Sozon Papavlasopoulos
Periodical of Key Engineering Materials 2015
Pedestrian navigation and shortest path: Preference versus distance
Iro Armeni, Konstantinos Chorianopoulos
Workshop, International Conference on Intelligent Environments 2013
Resume of the thesis "More than a machine" J. A. Coderch
Iro Armeni*, Telesilla Bristogianni*
Technical Chronicles, Technical Chamber of Greece 2020
Books & chapters
Books and chapters
Artificial Intelligence for Predicting Reuse Patterns
Iro Armeni, Deepika Raghu, Catherine De Wolf
in "A Circular Built Environment in the Digital Age"
Eds. Catherine De Wolf, Sultan Çetin, Nancy Bocken
Springer Nature
Miscellaneous
Selected conversations and stories
Panel discussion
Panel Discussion on Practical Applications of AI: On Construction
Iro Armeni
12th Thessaloniki International Symposium in World Affairs: "Prometheus' dilemma: The applications of AI in everyday life."
watch the discussionPodcast
Computer Vision and Mixed Reality in Architecture with Prof. Iro Armeni
Circular Engineering for Architecture Podcast, 2024
listen to the podcastShort story
A Day in the Life of an Architect in the Gradient World
Short Story, 2023
Iro Armeni
read the storyDatasets
Open data and resources
HouseTour, 2025
Over 1,200 house-tour videos with camera poses, 3D reconstructions, and real estate descriptions.
Website
Nothing Stands Still (NSS), 2024
3D point clouds from 6 large indoor building areas under construction or renovation, across 27 temporal stages.
Website
3D Scene Graph, 2019
Semantic annotations for Gibson environment models, including 3D/2D segmentations and object, room, and camera relationships.
Website
Stanford 2D-3D-Semantics Dataset (2D-3D-S), 2017
Registered RGB, depth, surface normal, and semantic annotations across 6,000+ m² of indoor space, with 3D meshes and point clouds.
Website
Stanford Large-Scale 3D Indoor Spaces Dataset (S3DIS), 2016
Point clouds of six large-scale indoor areas across three buildings, annotated with 12 building-element classes plus clutter.
Website