Zillow applied science teams are actively publishing their work. The areas of investigation include computer vision, document understanding, natural language processing (NLP), and recommendation systems. This webpage lists our publications, and where code is available, links are provided (with separate licenses).
Cruz, S., Hutchcroft, W., Li, Y., Khosravan, N., Boyadzhiev, I., & Kang, S. B. (2021). Zillow indoor dataset: Annotated floor plans with 360deg panoramas and 3D room layouts. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. [Paper] [Supplementary Material] [Code]
N. Nejatishahidin, W. Hutchcroft, M. Narayana, I. Boyadzhiev, Y. Li, N. Khosravan, J. Kosecka, and S.B. Kang (2023). Graph-CoVis: GNN-based Multi-view Panorama Global Pose Estimation. OmniCV, CVPR Workshop. (Best Paper Award)
P. Fayyazsanavi, Z. Wan, W. Hutchcroft, I. Boyadzhiev, Y. Li, J. Kosecka, and S.B. Kang (2023). U2RLE: Uncertainty-Guided 2-Stage Room Layout Estimation. CIVILS, CVPR Workshop.
J. Lambert, Y. Li, I. Boyadzhiev, L. Wixson, M. Narayana, W. Hutchcroft, J. Hays, F. Dellaert, & S.B. Kang (2022). SALVe: Semantic Alignment Verification for Floorplan Reconstruction from Sparse Panoramas. European Conference on Computer Vision (ECCV).
W. Hutchcroft, Y. Li, I. Boyadzhiev, Z. Wan, H. Wang, & S.B. Kang (2022). CoVisPose: Co-Visibility Pose Transformer for Wide-Baseline Relative Pose Estimation in 360 Indoor Panoramas. European Conference on Computer Vision (ECCV).
T. Zhi, B. Chen, I. Boyadzhiev, S.B. Kang, M. Hebert, & S.G. Narasimhan (2022). Semantically Supervised Appearance Decomposition for Virtual Staging from a Single Panorama. ACM TOG and SIGGRAPH. [Paper] [Code]
Y. Yin, W. Hutchcroft, N. Khosravan, I. Boyadzhiev, Y. Fu, & S.B. Kang (2022). Generating Topological Structure of Floorplans from Room Attributes. ACM International Conference on Multimedia Retrieval (ICMR). [Paper] [Code - Coming Soon]
Z. Min, N. Khosravan, Z. Bessinger, M. Narayana, S.B. Kang, E. Dunn, & I. Boyadzhiev (2022). LASER: LAtent SpacE Rendering for 2D Visual Localization. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). (Oral). [Paper] [Code]
H. Wang, W. Hutchcroft, Y. Li, Z. Wan, I. Boyadzhiev, Y. Tian, & S.B. Kang (2022). PSMNet: Position-aware Stereo Merging Network for Room Layout Estimation. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). [Paper] [Code]
Eder, M., Moulon, P., & Guan, L. (2019). Pano popups: Indoor 3D reconstruction with a plane-aware network. IEEE International Conference on 3D Vision (3DV). [Paper]
Zou, C., Colburn, A., Shan, Q., & Hoiem, D. (2018). Layoutnet: Reconstructing the 3d room layout from a single rgb image. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). [Paper] [Code]
Yan, H., Shan, Q., & Furukawa, Y. (2018). RIDI: Robust IMU double integration. In Proceedings of the European Conference on Computer Vision (ECCV). [Paper] [Code]
Izadinia, H., Shan, Q., & Seitz, S. M. (2017). Im2cad. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). [Paper]
Ikehata, S., Boyadzhiev, I., Shan, Q., & Furukawa, Y. (2016). Panoramic structure from motion via geometric relationship detection. arXiv preprint arXiv:1612.01256. [Report]
How the Zillow Indoor Dataset Facilitates Better 3D tours and Advances the Science of Indoor Spaces
Using SageMaker for Machine Learning Model Deployment with Zillow Floor Plans
Zillow Floor Plan: Training Models to Detect Windows, Doors and Openings in Panoramas
Computing at the Edge: On Device Stitching with Zillow 3D Homes
My Internship at Zillow Group AI Part 1: Attribute Recognition in Real Estate Listings
Behind Zillow 3D Home - Backend Algorithms
Vision & Deep Learning Meetup at Zillow on March 13
Organizing Real Estate Photo Collections for Visual Browsing
What Makes a Photo Click: Selecting Hero Images with Deep Learning
Deploying Deep Learning at Trulia
Rahmani, A. R., Li, L., Vanover, B., Bertrand, C., & Rawat, S. (2022). Towards Semantic Search for Community Question Answering for Mortgage Officers. Knowledge Discovery and Data Mining (KDD) Workshop on Document Understanding 2021. [Paper] [Video]
Zillow: Near Real-Time Natural Language Processing (NLP) for Customer Interactions
How Zillow and Genesys are transforming customer conversations
Building Speech Analytics Using AWS AI Services
Chakraborty, S., Shah, S., Soltani, K., Swigart, A., Yang, L., & Buckingham, K. (2020, December). Building an automated and self-aware anomaly detection system. In 2020 IEEE International Conference on Big Data (Big Data) (pp. 1465-1475). IEEE. [Paper] [Code]
Chau, H., Balaneshin, S., Liu, K., & Linda, O. (2020, December). Understanding the tradeoff between cost and quality of expert annotations for keyphrase extraction. In Proceedings of the 14th Linguistic Annotation Workshop (pp. 74-86). [Paper]
Chaudhari, H. A., Lin, S., & Linda, O. (2020). A General Framework for Fairness in Multistakeholder Recommendations. 3rd FAccTRec Workshop: Responsible Recommendation. Fourteenth ACM Conference on Recommender Systems. 2020. [Paper]
Harrison, Z., Khazane, A. (2022). Taxonomic Recommendations of Real Estate Properties with Textual Attribute Information. Proceedings of the 16th ACM Conference on Recommender Systems (RecSys '22). [Paper]
Klevak, E., Lin, S., Martin, A., Linda, O., & Ringger, E. (2020). Out-Of-Bag Anomaly Detection. The Third International TrueFact Workshop: Making a Credible Web for Tomorrow. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2021 [Paper]
Nichols, E., Xu, R., Thiagarajan, B., Kamath, S. (2022). Volume Governing for Email and Push Messages. Proceedings of the 16th ACM Conference on Recommender Systems (RecSys '22). [Paper]
Ringger, E., Chang, A., Fagnan, D., Kamath, S., Linda, O., Liu, W., ... & Zeghmi, T. (2018). Finding Your Home: Large-Scale Recommendation in a Vibrant Marketplace. ComplexRec 2018, 13. [Paper]
Using AI to Understand the Complexities and Pitfalls of Real Estate Data (April 2024)
Navigating Fair Housing Guardrails in LLMs (January 2024)
Helping Users Discover Their Dream Homes Through Home Insights Collections (February 2023)
How Zillow Data Science Measures Business Outcomes with Bayesian Statistics (February 2023)
Serving Machine Learning Models Efficiently at Scale at Zillow (November 2022)
Identifying High-Intent Buyers (November 2022)
Incorporating Listing Descriptions into the Zestimate (November 2022)
Helping Home Shoppers Find a Home to Love Through Home Insights (August 2022)
Optimizing Elasticsearch for Low Latency, Real-Time Recommendations (August 2022)
Improving Recommendation Quality by Tapping into Listing Text (February 2021)
Utilizing both Explicit & Implicit Signals to Power Home Recommendations (July 2020)
Topic Modeling for Real Estate Listing Descriptions (June 2019)
Home Embeddings for Similar Home Recommendations (October 2018)
#mlread: The Machine Learning Reading Group in Zillow AI (July 2018)
Visualizing Matrix Factorization Using Self-Organizing Maps (June 2018)
Personalized Location Preference for Home Recommendations (April 2018)
Introduction to Recommendations at Zillow (February 2017)
Moghimi, F., Johnson, R. A., & Krause, A. (2023). Rethinking Real Estate Pricing with Transformer Graph Neural Networks (T-GNN). In 2023 International Conference on Machine Learning and Applications (ICMLA) (pp. 1405-1411). IEEE. [Paper] [Code]
Krause, A., Martin, A., and Fix, M. (2020). Uncertainty in Automated Valuation Models: Error- vs Model-Based Approaches. Journal of Property Research, 37(4), 308-339. [Paper] [Code]
Home features and sales: Los Angeles, Orange and Ventura, California, up to 2017
Imputing Data for the Zestimate (November 2023)
Building the Neural Zestimate (February 2023)
Incorporting Listing Descriptions into the Zestimate
What's the Differences between a Machine and a Human Valuation
Advice from Kaggle on Entering ZillowPrize
Balancing Latency and Accuracy in the Zestimate
Home Value Estimates: Understanding Their Purposes And Evaluating Their Results