About

I'm a Staff Research Scientist at Google DeepMind in New York, where I work on the 3D understanding and generation capabilities of frontier models. I've contributed to the pretraining of Gemini 3 and Vision Banana, as well as several unannounced models. Before DeepMind, I built 2D3DNet at Google Research — in production across Google Maps since 2021, where it has driven over 30 million map updates. My research background is 3D computer vision, including 3D shape representation and scene understanding.

I received my Ph.D. from Princeton University, advised by Thomas Funkhouser in the Vision & Robotics Group. Before that, I studied Computer Science at Cornell University, where I worked with David Williamson on theoretical computer science and combinatorial optimization.

News

  • Jun 2026Recognized as an Outstanding Area Chair for CVPR 2026.
  • Apr 2026Vision Banana and CityRAG are out on arXiv.
  • Mar 2026Joined the SIGGRAPH Asia 2026 Technical Workshops Committee.
  • Jan 2026Joined the SIGGRAPH 2026 Technical Papers Committee.
  • Nov 2025Gemini 3 launches — I contributed geospatial pretraining data for its expert-level geoguessing capability.
  • Oct 2025Promoted to Staff Research Scientist at Google DeepMind.
  • Oct 2025Three papers at ICCV 2025 — MoMaps, Visual Chronicles, and SplatTalk — and served as an ICCV 2025 Area Chair.

Publications

2026
Vision Banana: Image Generators are Generalist Vision Learners
Valentin Gabeur, Shangbang Long, Songyou Peng, Paul Voigtlaender, …, Kyle Genova, …, Kaiming He, Thomas Funkhouser, Jean-Baptiste Alayrac, Radu Soricut (25 authors)
arXiv 2026arXivProject page
CityRAG: Stepping Into a City via Spatially-Grounded Video Generation
Gene Chou, Charles Herrmann, Kyle Genova, Boyang Deng, Songyou Peng, Bharath Hariharan, Jason Y. Zhang, Noah Snavely, Philipp Henzler
arXiv 2026arXivProject page
2025
MoMaps: Semantics-Aware Scene Motion Generation with Motion Maps
Jiahui Lei, Kyle Genova, George Kopanas, Noah Snavely, Leonidas Guibas
ICCV 2025arXivPaper
Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images
Boyang Deng, Songyou Peng, Kyle Genova, Gordon Wetzstein, Noah Snavely, Leonidas Guibas, Thomas Funkhouser
ICCV 2025arXivProject page
SplatTalk: 3D VQA with Gaussian Splatting
Anh Thai, Songyou Peng, Kyle Genova, Leonidas Guibas, Thomas Funkhouser
ICCV 2025arXivProject page
2024
LOC3DIFF: Local Diffusion for 3D Human Head Synthesis and Editing
Yushi Lan, Feitong Tan, Qiangeng Xu, Di Qiu, Kyle Genova, Zeng Huang, Sean Fanello, Rohit Pandey, Thomas Funkhouser, Chen Change Loy, Yinda Zhang
ECCV 2024Paper
NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis
Nilesh Kulkarni, Davis Rempe, Kyle Genova, Abhijit Kundu, Justin Johnson, David Fouhey, Leonidas Guibas
CVPR 2024arXivProject page
2023
Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervision
Xiaoshuai Zhang, Abhijit Kundu, Thomas Funkhouser, Leonidas Guibas, Hao Su, Kyle Genova
CVPR 2023arXivPaper
OpenScene: 3D Scene Understanding with Open Vocabularies
Songyou Peng, Kyle Genova, Chiyu "Max" Jiang, Andrea Tagliasacchi, Marc Pollefeys, Thomas Funkhouser
CVPR 2023arXivProject page
2022
Polynomial Neural Fields for Subband Decomposition and Manipulation
Guandao Yang*, Sagie Benaim*, Varun Jampani, Kyle Genova, Jonathan T. Barron, Thomas Funkhouser, Bharath Hariharan, Serge Belongie
NeurIPS 2022arXivCode
Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation
Abhijit Kundu, Kyle Genova, Xiaoqi Yin, Alireza Fathi, Caroline Pantofaru, Leonidas Guibas, Andrea Tagliasacchi, Frank Dellaert, Thomas Funkhouser
CVPR 2022arXivProject page
NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes
Suhani Vora, Noha Radwan, Klaus Greff, Henning Meyer, Kyle Genova, Mehdi S. M. Sajjadi, Etienne Pot, Andrea Tagliasacchi, Daniel Duckworth
TMLR 2022arXivProject page
2021
Learning 3D Semantic Segmentation with only 2D Image Supervision
Kyle Genova, Xiaoqi Yin, Abhijit Kundu, Caroline Pantofaru, Forrester Cole, Avneesh Sud, Brian Brewington, Brian Shucker, Thomas Funkhouser
3DV 2021OralarXiv
Multiresolution Deep Implicit Functions for 3D Shape Representation
Zhang Chen, Yinda Zhang, Kyle Genova, Sean Fanello, Sofien Bouaziz, Christian Häne, Ruofei Du, Cem Keskin, Thomas Funkhouser, Danhang Tang
ICCV 2021arXiv
Differentiable Surface Rendering via Non-differentiable Sampling
Forrester Cole, Kyle Genova, Avneesh Sud, Daniel Vlasic, Zhoutong Zhang
ICCV 2021arXiv
3D Representations for Learning to Reconstruct and Segment Shapes
Kyle Genova
Ph.D. ThesisPrinceton University
IBRNet: Learning Multi-View Image-Based Rendering
Qianqian Wang, Zhicheng Wang, Kyle Genova, Pratul P. Srinivasan, Howard Zhou, Jonathan T. Barron, Ricardo Martin-Brualla, Noah Snavely, Thomas Funkhouser
CVPR 2021arXivProject page
2020
Local Deep Implicit Functions for 3D Shape
Kyle Genova, Forrester Cole, Avneesh Sud, Aaron Sarna, Thomas Funkhouser
CVPR 2020OralarXivProject pageCodeVideo
CvxNet: Learnable Convex Decomposition
Boyang Deng, Kyle Genova, Soroosh Yazdani, Sofien Bouaziz, Geoffrey Hinton, Andrea Tagliasacchi
CVPR 2020Best Paper NomineearXivProject page
Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
Zeyu Wang, Klint Qinami, Ioannis Christos Karakozis, Kyle Genova, Prem Nair, Kenji Hata, Olga Russakovsky
CVPR 2020arXiv
2019
Learning Shape Templates with Structured Implicit Functions
Kyle Genova, Forrester Cole, Daniel Vlasic, Aaron Sarna, William T. Freeman, Thomas Funkhouser
ICCV 2019arXivCode
Text-based Editing of Talking-head Video
Ohad Fried, Ayush Tewari, Michael Zollhöfer, Adam Finkelstein, Eli Shechtman, Dan B. Goldman, Kyle Genova, Zeyu Jin, Christian Theobalt, Maneesh Agrawala
SIGGRAPH 2019arXivProject pageVideo (391K views)
2018 & earlier
Unsupervised Training for 3D Morphable Model Regression
Kyle Genova, Forrester Cole, Aaron Maschinot, Aaron Sarna, Daniel Vlasic, William T. Freeman
CVPR 2018SpotlightarXivPaper
Learning Where to Look: Data-Driven Viewpoint Set Selection for 3D Scenes
Kyle Genova, Manolis Savva, Angel X. Chang, Thomas Funkhouser
arXiv 2017arXiv
An Experimental Evaluation of the Best-of-Many Christofides' Algorithm for the Traveling Salesman Problem
Kyle Genova, David P. Williamson
Algorithmica 2017ESA 2015ESA Selected PublicationarXiv

Academic Service

  • Area Chair — CVPR 2026 (Outstanding Area Chair); ICCV 2025; SIGGRAPH 2026 (Technical Papers Committee)
  • Technical Workshops Committee — SIGGRAPH Asia 2026
  • Reviewer — CVPR (2025, 2022, 2021 Outstanding Reviewer, 2020, 2019, 2018), ICCV (2023, 2021, 2019), ECCV (2024, 2022, 2020 Outstanding Reviewer), NeurIPS (2025 Top Reviewer, 2019 Top Reviewer), SIGGRAPH (2024, 2023, 2022, 2020), SIGGRAPH Asia (2024, 2023, 2022, 2021, 2019), OpenSUN3D 2024

Awards & Fellowships

  • Siebel Scholar, Class of 2021 — The Thomas and Stacey Siebel Foundation, 2020
  • NSF Graduate Research Fellowship — National Science Foundation, 2018–2021
  • Graduate Student Teaching Award — Princeton University, 2018
  • Gordon Y.S. Wu Fellowship in Engineering — Princeton University, 2016–2021
  • Phi Beta Kappa — Cornell University, 2015
  • CRA Outstanding Undergraduate Researcher Nomination — Cornell University, 2015
  • Hatton Lovejoy Scholarship — Fuller E. Callaway Foundation, 2012–2016

Teaching

  • Princeton University, Assistant in Instruction — Computer Graphics (COS 426, Spring 2018), Computer Vision (COS 429, Fall 2017)
  • Cornell University, Teaching Assistant — Analysis of Algorithms (CS 4820, Spring 2016), Computer Graphics (CS 4620, Fall 2015), Data Structures & Functional Programming (CS 3110, Fall 2014)