Kyle Genova

About Me

I'm a Research Scientist at Google, on Thomas Funkhouser's team in the CCI vision research group led by Bill Freeman and David Salesin. My work is at the intersection of 3D computer vision and graphics, particularly in shape representation, differentiable rendering, and scene understanding.

Previously, I was a Ph.D. student at Princeton University, where I was also advised by Thomas Funkhouser in the Vision & Robotics Group. Before that, I was an undergraduate in Computer Science at Cornell University, where I worked with David Williamson in the areas of theoretical computer science and combinatorial optimization.

Research

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 2023 and arXiv
Project page

OpenScene: 3D Scene Understanding with Open Vocabularies
Songyou Peng, Kyle Genova, Chiyu "Max" Jiang, Andrea Tagliasacchi, Marc Pollefeys, Thomas Funkhouser
CVPR 2023 and arXiv
Project page

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 2022 and arXiv
Project page

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 2022 and arXiv
Project page

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 2021 (Oral) and arXiv

NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes
Suhani Vora, Noha Radwan, Klaus Greff, Henning Meyer, Kyle Genova, Mehdi SM Sajjadi, Etienne Pot, Andrea Tagliasacchi, Daniel Duckworth
TMLR 2022 and arXiv
Project page

Multiresolution Deep Implicit Functions for 3D Shape Representation
Zhang Chen, Yinda Zhang, Kyle Genova, Sean Fanello, Sofien Bouaziz, Christian Häne, Roufei Du, Cem Keskin, Thomas Funkhouser, Danhang Tang
ICCV 2021 and arXiv

Differentiable Surface Rendering via Non-differentiable Sampling
Forrester Cole, Kyle Genova, Avneesh Sud, Daniel Vlasic, Zhoutong Zhang
ICCV 2021 and arXiv

3D Representations for Learning to Reconstruct and Segment Shapes
Kyle Genova
Thesis (Hosted at Princeton 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, Noaha Snavely, Thomas Funkhouser
CVPR 2021 and arXiv

Local Deep Implicit Functions for 3D Shape
Kyle Genova, Forrester Cole, Avneesh Sud, Aaron Sarna, Thomas Funkhouser
CVPR 2020 (Oral) and arXiv Formerly "Deep Structured Implicit Functions"
Project page, Video, and Code

CvxNet: Learnable Convex Decomposition
Boyang Deng, Kyle Genova, Soroosh Yazdani, Sofien Bouaziz, Geoffrey Hinton, Andrea Tagliasacchi
CVPR 2020 (Best Paper Nominee) and arXiv

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 2020 and arXiv

Learning Shape Templates with Structured Implicit Functions
Kyle Genova, Forrester Cole, Daniel Vlasic, Aaron Sarna, William T. Freeman, Thomas Funkhouser
ICCV 2019 and arXiv
Code

Text-based Editing of Talking-head Video
Ohad Fried, Ayush Tewari, Michael Zollhöfer, Adam Finkelstein, Eli Schechtman, Dan B. Goldman, Kyle Genova, Zeyu Jin, Christian Theobalt, Maneesh Agrawala
SIGGRAPH 2019 and arXiv
Video (300K Views) and project page

Unsupervised Training for 3D Morphable Model Regression
Kyle Genova, Forrester Cole, Aaron Maschinot, Aaron Sarna, Daniel Vlasic, William T. Freeman
CVPR 2018 (Spotlight) and arXiv

Learning Where to Look: Data-Driven Viewpoint Set Selection for 3D Scenes
Kyle Genova, Manolis Savva, Angel X. Chang, Thomas Funkhouser
arXiv

An Experimental Evaluation of the Best-of-Many Christofides' Algorithm for the Traveling Salesman Problem
Kyle Genova and David P. Williamson
Algorithmica 2017 (Selected Publication), ESA 2015, and arXiv

Fellowships & Scholarships

NSF GRFP
National Science Foundation, 2018-2022

Gordon Y.S. Wu Fellowship in Engineering
Princeton Unversity, 2016-2021

Hatton Lovejoy Scholarship
Fuller E. Callaway Foundation, 2012-2016

Valtarese Foundation Scholarship
Valtarese Foundation, 2012

Awards

Class of 2021 Siebel Scholar
The Thomas and Stacey Siebel Foundation, 2020

Graduate Student Teaching Award
Princeton University, 2018

Phi Beta Kappa
Cornell University, 2015

Computing Research Association Oustanding Undergraduate Researcher Nomination
Cornell University, 2015

Internships

Multiple Projects
Google
Ph.D. Internship, Mountain View, CA, 2019-2021
Long-term internship in Machine Perception Group.

Learning Shape Templates with Structured Implicit Functions
Google
Ph.D. Internship, Cambridge, MA, 2018
Cambridge Vision Research Group, with Aaron Sarna and Bill Freeman

Unsupervised Training for 3D Morphable Model Regression
Google
Ph.D. Internship, Cambridge, MA, 2017
Cambridge Vision Research Group, with Forrester Cole and Bill Freeman

In-Memory K-Way Balanced Graph Partitioning
Google
Ph.D. Internship, New York, NY, 2016
NYC Algorithms Research Group, with Aaron Archer and Vahab Mirrokni

Reviewing

ECCV 2022, 2020 Outstanding Reviewer
CVPR 2022, 2021 Outstanding Reviewer, 2020, 2019, 2018
NeurIPS 2019 Top Reviewer
ICCV 2023, 2021, 2019
SIGGRAPH 2023, 2022, 2020
SIGGRAPH Asia 2022, 2021, 2019

Teaching

Princeton University, Assistant in Instruction
Computer Graphics, COS426 Spring 2018
Computer Vision, COS 429 Fall 2017

Cornell University, Teaching Assistant
Intro to Analysis of Algorithms, CS 4820 Spring 2016
Computer Graphics, CS 4620 Fall 2015
Data Structures and Functional Programming, CS 3110 Fall 2014