Philipp Henzler

Research Scientist, Google

I am a Research Scientist at Google working on agents, world models (Genie) and video models (Gemini Omni). I received my PhD from University College London supervised by Tobias Ritschel and Niloy J. Mitra. My PhD thesis received the Eurographics PhD Thesis award 2024. I received my BSc and MSc from Ulm University in Germany where I am originally from.

Product Impact

Genie

Google DeepMind and collaborators

Flow, 2026

Google DeepMind's real-time interactive world model.

Project page

Gemini Omni

Omni team and collaborators at Google DeepMind

Gemini / Flow, 2026

A video model that creates videos from any input.

Project page

Veo 2/3

Veo team and collaborators at Google DeepMind

Flow, 2025

Google DeepMind's state of the art generative video model with audio.

Project page

Google Search 360-spins

Team and collaborators at Google

Google Search, 2022-2025

AI-generated 360-degree spins of products.

Project page

Research

PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation

Haofei Xu, Rundi Wu, Philipp Henzler, Nikolai Kalischeck, Michael Oechsle, Fabian Manhardt, Marc Pollefeys, Andreas Geiger, Federico Tombari, Michael Niemeyer

ICML, 2026

Project page arXiv

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

NeurIPS, 2026 Spotlight

Project page arXiv

UFO-4D: Unposed Feedforward 4D Reconstruction from Two Images

Junhwa Hur, Charles Herrmann, Songyou Peng, Philipp Henzler, Zeyu Ma, Todd Zickler, Deqing Sun

ICLR, 2026

Project page arXiv

GR3EN: Generative Relighting for 3D Environments

Xiaoyan Xing, Philipp Henzler, Junhwa Hur, Runze Li, Jonathan T. Barron, Pratul P. Srinivasan, Dor Verbin

SIGGRAPH, 2026

Project page arXiv

VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compression

Kyle Sargent, Ruiqi Gao, Philipp Henzler, Charles Herrmann, Aleksander Holynski, Fei-Fei Li, Jiajun Wu, Jason Y. Zhang

CVPR, 2026

Project page arXiv

Gen2Physics: Grounding Generated 3D Meshes in Physics via Multi-View Material Decomposition

Mauro Comi, Jordi Serrano Berbel, Kevis-Kokitsi Maninis, Philipp Henzler, Manuel Sanchez

arXiv, 2026

arXiv

FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation

Orest Kupyn, Goutam Bhat, Philipp Henzler, Fabian Manhardt, Christian Rupprecht, Federico Tombari

arXiv, 2026

Project page arXiv

ROGR: Relightable 3D Objects Using Generative Relighting

Jiapeng Tang, Matthew Levine, Dor Verbin, Stephan J. Garbin, Matthias Nießner, Ricardo Martin-Brualla, Pratul P. Srinivasan, Philipp Henzler

NeurIPS, 2025 Spotlight (top 3.2%)

Project page arXiv

Bolt3D: Generating 3D Scenes in Seconds

Stanislaw Szymanowicz, Jason Y. Zhang, Pratul P. Srinivasan, Ruiqi Gao, Arthur Brussee, Aleksander Holynski, Ricardo Martin-Brualla, Jonathan T. Barron, Philipp Henzler

ICCV, 2025

Project page arXiv

CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation

Nikolai Kalischeck, Michael Oechsle, Fabian Manhardt, Philipp Henzler, Konrad Schindler, Federico Tombari

ICLR, 2025 Spotlight (top 3.3%)

Project page arXiv

Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation

Hadi Alzayer, Philipp Henzler, Jonathan T. Barron, Jia-Bin Huang, Pratul P. Srinivasan, Dor Verbin

CVPR, 2025 Highlight (top 3%)

Project page arXiv

Can Generative Video Models Help Pose Estimation?

Ruojin Cai, Jason Y. Zhang, Philipp Henzler, Zhengqi Li, Noah Snavely, Ricardo Martin-Brualla

CVPR, 2025 Highlight (top 3%)

Project page arXiv

SimVS: Simulating World Inconsistencies for Robust View Synthesis

Alex Trevithick, Roni Paiss, Philipp Henzler, Dor Verbin, Rundi Wu, Hadi Alzayer, Ruiqi Gao, Ben Poole, Jonathan T. Barron, Aleksander Holynski, Ravi Ramamoorthi, Pratul P. Srinivasan

CVPR, 2025

Project page arXiv

IllumiNeRF: 3D Relighting without Inverse Rendering

Xiaoming Zhao, Pratul P. Srinivasan, Dor Verbin, Keunhong Park, Ricardo Martin-Brualla, Philipp Henzler

NeurIPS, 2024

Project page arXiv

CAT3D: Create Anything in 3D with Multi-View Diffusion Models

Ruiqi Gao, Aleksander Holynski, Philipp Henzler, Arthur Brussee, Ricardo Martin-Brualla, Pratul P. Srinivasan, Jonathan T. Barron, Ben Poole

NeurIPS, 2024 Oral (top 0.4%)

Project page arXiv

ReconFusion: 3D Reconstruction with Diffusion Priors

Rundi Wu, Ben Mildenhall, Philipp Henzler, Keunhong Park, Ruiqi Gao, Daniel Watson, Pratul P. Srinivasan, Dor Verbin, Jonathan T. Barron, Ben Poole, Aleksander Holynski

CVPR, 2024

Project page arXiv