Philipp Henzler

Research Scientist, Google

I am a Research Scientist at Google working on 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

Gemini Omni

Gemini Omni

Omni team and collaborators at Google DeepMind
Gemini / Flow, 2026
A video generation model that creates videos from any input.
Project page
Veo 2/3

Veo 2/3

Veo team and collaborators at Google DeepMind
Flow, 2025-2026
Google DeepMind's generative video model.
Project page
3D Shoppable Products

3D Shoppable Products

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

PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation

ICML, 2026
Project page arXiv
FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation

FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation

arXiv, 2026
Project page arXiv
CityRAG: Stepping Into a City via Spatially-Grounded Video Generation

CityRAG: Stepping Into a City via Spatially-Grounded Video Generation

arXiv, 2026
Project page arXiv
UFO-4D: Unposed Feedforward 4D Reconstruction from Two Images

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

ICLR, 2026
Project page arXiv
GR3EN: Generative Relighting for 3D Environments

GR3EN: Generative Relighting for 3D Environments

SIGGRAPH, 2026
Project page arXiv
VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compression

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

CVPR, 2026
Project page arXiv
ROGR: Relightable 3D Objects Using Generative Relighting

ROGR: Relightable 3D Objects Using Generative Relighting

NeurIPS, 2025 Spotlight
Project page arXiv
Bolt3D: Generating 3D Scenes in Seconds

Bolt3D: Generating 3D Scenes in Seconds

ICCV, 2025
Project page arXiv
CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation

CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation

ICLR, 2025 Spotlight
Project page arXiv
Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation

Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation

CVPR, 2025 Highlight
Project page arXiv
Can Generative Video Models Help Pose Estimation?

Can Generative Video Models Help Pose Estimation?

CVPR, 2025 Highlight
Project page arXiv
SimVS: Simulating World Inconsistencies for Robust View Synthesis

SimVS: Simulating World Inconsistencies for Robust View Synthesis

CVPR, 2025
Project page arXiv
IllumiNeRF: 3D Relighting without Inverse Rendering

IllumiNeRF: 3D Relighting without Inverse Rendering

NeurIPS, 2024
Project page arXiv
CAT3D: Create Anything in 3D with Multi-View Diffusion Models

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

NeurIPS, 2024 Oral
Project page arXiv
ReconFusion: 3D Reconstruction with Diffusion Priors

ReconFusion: 3D Reconstruction with Diffusion Priors

CVPR, 2024
Project page arXiv
CamP: Camera Preconditioning for Neural Radiance Fields

CamP: Camera Preconditioning for Neural Radiance Fields

SIGGRAPH Asia, 2023 Journal Paper
Project page arXiv
Self-Supervised Shape and Appearance Modeling via Neural Differentiable Graphics

Self-Supervised Shape and Appearance Modeling via Neural Differentiable Graphics

Philipp Henzler
University College London (UCL), PhD thesis, 2023 Eurographics PhD Thesis Award
Project page PDF
Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction

Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction

ICCV 2021 Oral, Best Paper Honorable Mention
Project page PDF arXiv Code Dataset
Generative Modelling of BRDF Textures from Flash Images

Generative Modelling of BRDF Textures from Flash Images

SIGGRAPH ASIA 2021 Journal Paper
Project page arXiv Dataset
Unsupervised Learning of 3D Object Categories from Videos in the Wild

Unsupervised Learning of 3D Object Categories from Videos in the Wild

CVPR 2021
Project page PDF arXiv
Learning a Neural 3D Texture Space from 2D Exemplars

Learning a Neural 3D Texture Space from 2D Exemplars

Philipp Henzler, Niloy J. Mitra, Tobias Ritschel
CVPR 2020
Project page PDF arXiv Dataset
Escaping Plato's Cave: 3D Shape From Adversarial Rendering

Escaping Plato's Cave: 3D Shape From Adversarial Rendering

Philipp Henzler, Niloy J. Mitra, Tobias Ritschel
ICCV 2019
Project page PDF arXiv Code
Deep Object Tracking on Dynamic Occupancy Grid Maps Using RNNs

Deep Object Tracking on Dynamic Occupancy Grid Maps Using RNNs

ITSC 2018
PDF
Object Detection on Dynamic Occupancy Grid Maps Using Deep Learning and Automatic Label Generation

Object Detection on Dynamic Occupancy Grid Maps Using Deep Learning and Automatic Label Generation

IV 2018
PDF
Single-Image Tomography: 3D Volumes from 2D Cranial X-Rays

Single-Image Tomography: 3D Volumes from 2D Cranial X-Rays

Eurographics 2018
PDF Code
Unconstrained Pedestrian Navigationbased on Vibro-tactile Feedback around the Wristband of a Smartwatch

Unconstrained Pedestrian Navigationbased on Vibro-tactile Feedback around the Wristband of a Smartwatch

David Dobbelstein, Philipp Henzler, Enrico Rukzio
CHI 2016
PDF

This template is borrowed from Keunhong Park.