Philipp Henzler

Research Scientist

henzler.github.io
henzler
philipphenzler
philipphenzler14@gmail.com

Employment

Google New York City / San Francisco, USA | London, UK
Senior Research Scientist, Agents, World/Video Models
2024 - Present
Research Scientist, Generative 3D Modeling
2022 - 2024
Adobe Research London, UK
Research Intern, Texture/Material Modeling
2021
Meta AI London, UK
Research Intern, 3D Reconstruction
2020
Robert Bosch GmbH / Ulm University Ulm, GER
Research Assistant, Autonomous Driving
2017 - 2018

Education

Ph.D. in Computer Science at University College London (UCL)
2018 - 2023
Advisors: Tobias Ritschel and Niloy J. Mitra
M.Sc. in Media Informatics at Ulm University
2015 - 2017
Advisor: Timo Ropinski
B.Sc. in Media Informatics at Ulm University
2012 - 2015
Advisor: Enrico Rukzio

Product Impact

Gemini Omni A video model that creates videos from any input.
2026
Veo 2/3 Google DeepMind's state of the art generative video model with audio.
2025
Google Search 360-spins AI-generated 360-degree spins of products.
2022-2025

Awards & Honors

Eurographics PhD Thesis Award
2024
ICCV Best Paper Honourable Mention
2021
Rabin Ezra Scholarship
2021
Google Fellowship & Department of Computer Science UCL Scholarship
2018
Winner of the Audi-App Challenge
2016

Publications

[27]
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
ICML, 2026
H. Xu, R. Wu, P. Henzler, N. Kalischeck, M. Oechsle, F. Manhardt, M. Pollefeys, A. Geiger, F. Tombari, M. Niemeyer
[26]
CityRAG: Stepping Into a City via Spatially-Grounded Video Generation
NeurIPS, 2026 Spotlight
G. Chou, C. Herrmann, K. Genova, B. Deng, S. Peng, B. Hariharan, J. Zhang, N. Snavely, P. Henzler
[25]
UFO-4D: Unposed Feedforward 4D Reconstruction from Two Images
ICLR, 2026
J. Hur, C. Herrmann, S. Peng, P. Henzler, Z. Ma, T. Zickler, D. Sun
[24]
GR3EN: Generative Relighting for 3D Environments
SIGGRAPH, 2026
X. Xing, P. Henzler, J. Hur, R. Li, J. T. Barron, P. P. Srinivasan, D. Verbin
[23]
VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compression
CVPR, 2026
K. Sargent, R. Gao, P. Henzler, C. Herrmann, A. Holynski, F. Li, J. Wu, J. Zhang
[22]
Gen2Physics: Grounding Generated 3D Meshes in Physics via Multi-View Material Decomposition
arXiv, 2026
M. Comi, J. Serrano Berbel, K. Maninis, P. Henzler, M. Sanchez
[21]
FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation
arXiv, 2026
O. Kupyn, G. Bhat, P. Henzler, F. Manhardt, C. Rupprecht, F. Tombari
[20]
ROGR: Relightable 3D Objects Using Generative Relighting
NeurIPS, 2025 Spotlight
J. Tang, M. Levine, D. Verbin, S. Garbin, M. Nießner, R. Martin-Brualla, P. P. Srinivasan, P. Henzler
[19]
Bolt3D: Generating 3D Scenes in Seconds
ICCV, 2025
S. Szymanowicz, J. Zhang, P. P. Srinivasan, R. Gao, A. Brussee, A. Holynski, R. Martin-Brualla, J. T. Barron, P. Henzler
[18]
CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation
ICLR, 2025 Spotlight
N. Kalischeck, M. Oechsle, F. Manhardt, P. Henzler, K. Schindler, F. Tombari
[17]
Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation
CVPR, 2025 Highlight
H. Alzayer, P. Henzler, J. T. Barron, J. Huang, P. P. Srinivasan, D. Verbin
[16]
Can Generative Video Models Help Pose Estimation?
CVPR, 2025 Highlight
R. Cai, J. Zhang, P. Henzler, Z. Li, N. Snavely, R. Martin-Brualla
[15]
SimVS: Simulating World Inconsistencies for Robust View Synthesis
CVPR, 2025
A. Trevithick, R. Paiss, P. Henzler, D. Verbin, R. Wu, H. Alzayer, R. Gao, B. Poole, J. T. Barron, A. Holynski, R. Ramamoorthi, P. P. Srinivasan
[14]
IllumiNeRF: 3D Relighting without Inverse Rendering
NeurIPS, 2024
X. Zhao, P. P. Srinivasan, D. Verbin, K. Park, R. Martin-Brualla, P. Henzler
[13]
CAT3D: Create Anything in 3D with Multi-View Diffusion Models
NeurIPS, 2024 Oral
R. Gao, A. Holynski, P. Henzler, A. Brussee, R. Martin-Brualla, P. P. Srinivasan, J. T. Barron, B. Poole
[12]
ReconFusion: 3D Reconstruction with Diffusion Priors
CVPR, 2024
R. Wu, B. Mildenhall, P. Henzler, K. Park, R. Gao, D. Watson, P. P. Srinivasan, D. Verbin, J. T. Barron, B. Poole, A. Holynski
[11]
CamP: Camera Preconditioning for Neural Radiance Fields
SIGGRAPH Asia, 2023 Journal Paper
K. Park, P. Henzler, B. Mildenhall, J. T. Barron, R. Martin-Brualla
[10]
Self-Supervised Shape and Appearance Modeling via Neural Differentiable Graphics
University College London (UCL), PhD thesis, 2023 Eurographics PhD Thesis Award
P. Henzler
[9]
Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction
ICCV 2021 Oral, Best Paper Honorable Mention
J. Reizenstein, R. Shapovalov, P. Henzler, L. Sbodorne, P. Labatut, D. Novotny
[8]
Generative Modelling of BRDF Textures from Flash Images
SIGGRAPH ASIA 2021 Journal Paper
P. Henzler, V. Deschaintre, N. J. Mitra, T. Ritschel
[7]
Unsupervised Learning of 3D Object Categories from Videos in the Wild
CVPR 2021
P. Henzler, J. Reizenstein, P. Labatut, R. Shapovalov, T. Ritschel, A. Vedaldi, D. Novotny
[6]
Learning a Neural 3D Texture Space from 2D Exemplars
CVPR 2020
P. Henzler, N. J. Mitra, T. Ritschel
[5]
Escaping Plato's Cave: 3D Shape From Adversarial Rendering
ICCV 2019
P. Henzler, N. J. Mitra, T. Ritschel
[4]
Deep Object Tracking on Dynamic Occupancy Grid Maps Using RNNs
ITSC 2018
N. Engel, S. Hoermann, P. Henzler, K. Dietmayer
[3]
Object Detection on Dynamic Occupancy Grid Maps Using Deep Learning and Automatic Label Generation
IV 2018
S. Hoermann, P. Henzler, M. Bach, K. Dietmayer
[2]
Single-Image Tomography: 3D Volumes from 2D Cranial X-Rays
Eurographics 2018
P. Henzler, V. Rasche, T. Ropinski, T. Ritschel
[1]
Unconstrained Pedestrian Navigationbased on Vibro-tactile Feedback around the Wristband of a Smartwatch
CHI 2016
D. Dobbelstein, P. Henzler, E. Rukzio

Invited Talks & Panels

3D GenAI, Physical AI, World Models
NYC Tech Week
June 2026
Generative 3D Content Creation
GenRecon3D Workshop, CVPR 2026
June 2026
Ulm University
December 2025
Korea Advanced Institute of Science and Technology (KAIST)
November 2025
AI3DCC Workshop, ICCV 2025
October 2025
Why 3D Matters: The Future of Video Models Depends On It
Amazon
March 2025
Meta
March 2025
Self-Supervised Shape and Appearance Modelling via Neural Differentiable Graphics
Apple
June 2022
Netflix
May 2022
Google
April 2022
Lund University
April 2022
National Institute for Research in Digital Science and Technology (Inria)
March 2022
Understanding Our World in 3D
Rabin Ezra Scholarship Trust
2021
Single-Image Tomography: 3D Volumes from 2D Cranial X-Rays
Eurographics
April 2018
University College London (UCL)
March 2018

Academic Service

Area Chair: ICML, ICLR
Program Committee: Eurographics
Reviewer: CVPR, ICCV, ECCV, SIGGRAPH, SIGGRAPH Asia, EG, TPAMI, TCVG, NeurIPS, CGF

Mentored Students and Interns

Xiaoyan Xing (University of Amsterdam) [24], 2026
Orest Kupyn (University of Oxford) [21], 2026
Mauro Comi (University of Bristol) [22], 2026
Kyle Sargent (Stanford University) [23], 2026
Haofei Xu (ETH Zurich) [27], 2026
Gene Chou (Cornell University) [26], 2026
Stanislaw Szymanowicz (University of Oxford) [19], 2025
Ruojin Cai (Cornell University) [16], 2025
Nikolai Kalischeck (ETH Zurich) [18], 2025
Jiapeng Tang (Technical University of Munich) [20], 2025
Hadi Alzayer (University of Maryland) [17], 2025
Alex Trevithick (UC San Diego) [15], 2025
Xiaoming Zhao (University of Illinois Urbana-Champaign) [14], 2024
Demian Till (University College London) 2021