Peter Hedman

- Senior Research Scientist, Google DeepMind (London) [firstname].j.[lastname]@gmail.com Twitter Google Scholar
Peter Hedman

Hi! I'm Peter Hedman, a researcher at Google DeepMind in London.

My focus is on creating immersive 3D experiences from easy-to-capture footage of real places. For example, you may want to scan and digitally revisit your childhood home, or capture a VR-ready 3D panorama of the places you visit during a vacation.

Formally, my research interests are view synthesis, image-based rendering, neural rendering and real-time graphics.

PUBLICATIONS

Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesis
(creiser.github.io/binary_opacity_grid)
 Christian Reiser, Stephan Garbin, Pratul Srinivasan, Dor Verbin, Richard Szeliski, Ben Mildenhall, Jonathan T. Barron, Peter Hedman*, Andreas Geiger*
SIGGRAPH 2024
SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Exploration
(smerf-3d.github.io)
 Daniel Duckworth*, Peter Hedman*, Christian Reiser, Peter Zhizhin, Jean-François Thibert, Mario Lučić, Richard Szeliski, Jonathan T. Barron
SIGGRAPH 2024 (Honorable Mention)
InterNeRF: Scaling Radiance Fields via Parameter Interpolation
(arxiv.org/abs/2406.11737)
 Clinton Wang, Peter Hedman, Polina Golland, Jonathan T. Barron, Daniel Duckworth
CVPR Neural Rendering Intelligence 2024
Eclipse: Disambiguating Illumination and Materials using Unintended Shadows
(dorverbin.github.io/eclipse)
 Dor Verbin, Ben Mildenhall, Peter Hedman, Jonathan T. Barron, Todd Zickler, Pratul Srinivasan
CVPR 2024 (Oral)
Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusion
(inpaint3d.github.io)
 Kira Prabhu*, Jane Wu*, Lynn Tsai*, Peter Hedman, Dan B Goldman, Ben Poole, Michael Broxton
arXiv 2023
Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields
(jonbarron.info/zipnerf)
 Jonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul Srinivasan, Peter Hedman
ICCV 2023 (Oral, Best Paper Finalist)
Vox-E: Text-guided Voxel Editing of 3D Objects
(tau-vailab.github.io/Vox-E)
 Etai Sella, Gal Fiebelman, Peter Hedman, Hadar Averbuch-Elor
ICCV 2023
MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes
(creiser.github.io/merf)
 Christian Reiser, Richard Szeliski, Dor Verbin, Pratul Srinivasan, Ben Mildenhall, Andreas Geiger, Jonathan T. Barron, Peter Hedman
SIGGRAPH 2023
BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis
(bakedsdf.github.io)
 Lior Yariv*, Peter Hedman*, Christian Reiser, Dor Verbin, Pratul Srinivasan, Richard Szeliski, Jonathan T. Barron, Ben Mildenhall
SIGGRAPH 2023
MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures
(mobile-nerf.github.io)
 Zhiqin Chen, Thomas Funkhouser, Peter Hedman, Andrea Tagliasacchi
CVPR 2023 (Best Paper Award Candidate)
AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training
(yifanjiang19.github.io/alignerf)
 Yifan Jiang, Peter Hedman, Ben Mildenhall, Dejia Xu, Jonathan T. Barron, Zhangyang Wang, Tianfan Xue
CVPR 2023
NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images
(bmild.github.io/rawnerf)
 Ben Mildenhall, Peter Hedman, Ricardo Martin-Brualla, Pratul Srinivasan, Jonathan T. Barron
CVPR 2022 (Oral)
Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
(jonbarron.info/mipnerf360)
 Jonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan and Peter Hedman
CVPR 2022 (Oral)
Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields
(dorverbin.github.io/refnerf)
 Dor Verbin, Peter Hedman, Ben Mildenhall, Todd Zickler, Jonathan T. Barron and Pratul P. Srinivasan
CVPR 2022 (Oral, Best Student Paper Honorable Mention), TPAMI 2024
HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields
(hypernerf.github.io)
 Keunhong Park, Utkarsh Sinha, Peter Hedman, Jonathan T. Barron, Sofien Bouaziz, Dan B. Goldman, Ricardo Martin-Brualla and Steven M. Seitz
SIGGRAPH Asia 2021
Baking Neural Radiance Fields for Real-Time View Synthesis
(nerf.live)
 Peter Hedman, Pratul P. Srinivasan, Ben Mildenhall, Jonathan T. Barron and Paul Debevec
ICCV 2021 (Oral), TPAMI 2024
Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields
(jonbarron.info/mipnerf)
 Jonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman, Ricardo Martin-Brualla and Pratul P. Srinivasan
ICCV 2021 (Oral, Best Paper Honorable Mention)
Immersive Light Field Video with a Layered Mesh Representation
(augmentedperception.github.io/deepviewvideo)
 Michael Broxton, John Flynn, Ryan Overbeck, Daniel Erickson, Peter Hedman, Matthew DuVall, Jason Dourgarian, Jay Busch, Matt Whalen and Paul Debevec
SIGGRAPH 2020
Image-Based Rendering of Cars using Semantic Labels and Approximate Reflection Flow
(repo-sam.inria.fr/fungraph/ibr-cars-semantic)
 Simon Rodriguez, Siddhant Prakash, Peter Hedman and George Drettakis
I3D 2020
Deep Blending for Free-Viewpoint Image-Based Rendering
(visual.cs.ucl.ac.uk/pubs/deepblending)
 Peter Hedman, Julien Philip, True Price, Jan-Michael Frahm, George Drettakis and Gabriel Brostow
SIGGRAPH Asia 2018
Instant 3D Photography
(visual.cs.ucl.ac.uk/pubs/instant3d)
 Peter Hedman and Johannes Kopf
SIGGRAPH 2018
Casual 3D Photography
(visual.cs.ucl.ac.uk/pubs/casual3d)
 Peter Hedman, Suhib Alsisan, Richard Szeliski and Johannes Kopf
SIGGRAPH Asia 2017
Scalable Inside-Out Image-Based Rendering
(visual.cs.ucl.ac.uk/pubs/insideout)
 Peter Hedman, Tobias Ritschel, George Drettakis and Gabriel Brostow
SIGGRAPH Asia 2016
Sequential Monte Carlo Instant Radiosity
(visual.cs.ucl.ac.uk/pubs/smcir)
 Peter Hedman, Tero Karras and Jaakko Lehtinen
I3D 2016, TVCG 2017
Multi-view Reconstruction of Highly Specular Surfaces in Uncontrolled Environments
(visual.cs.ucl.ac.uk/pubs/shapefromreflections)
 Clément Godard*, Peter Hedman*, Wenbin Li and Gabriel J. Brostow
3DV 2015 (Oral) *Joint first authors.

JOB EXPERIENCE

May 2024 Google DeepMind, Senior Research Scientist, London U.K.
Working on Neural Radiance Fields.
May 2022 - May 2024 Google, Senior Research Scientist, London U.K.
Working on Neural Radiance Fields.
Nov 2020 - May 2022 Google, Research Scientist, London U.K.
Working on Neural Radiance Fields.
Nov 2019 - Nov 2020 Google, Research Scientist, Los Angeles USA.
Worked on Immersive Light Field Video with a Layered Mesh Representation (SIGGRAPH 2020).
Jun 2017 - Aug 2018 Pro Unlimited, Contingent worker @ Facebook (Computational photography group), London U.K.
Developed Instant 3D Photography (SIGGRAPH 2018).
Jun 2016 - Jun 2017 Facebook, PhD research intern (Computational photography group), Seattle USA.
Developed Casual 3D Photography (SIGGRAPH Asia 2017).
Dec 2013 - May 2014 NVIDIA, research intern (NVIDIA research), Helsinki Finland.
Developed Sequential Monte Carlo Instant Radiosity (I3D 2016, TVCG 2017).
Jan 2012 - Nov 2013 NVIDIA, Systems software engineer (mobile browser team), Helsinki Finland.
Worked with a heavily threaded C++, HTML5 Canvas, WebGL, WebKit, Skia and OpenGL ES2.
May 2011 - Jan 2012 NVIDIA, software engineering intern (Flash3D team), Helsinki Finland.
Optimized Flash3D for NVIDIA Tegra.

AWARDS AND MEDIA

Dec 2021 - Jan 2022 Publicity for HyperNeRF (Two Minute Papers, Gigazine, 80 Level).
Mar 2021 - Apr 2021 Publicity for Baking Neural Radiance Fields for Real-Time View Synthesis (Marktechpost, Synced).
Jun 2020 - Jan 2021 Publicity for Immersive Light Field Video with a Layered Mesh Representation (TechCrunch, Two Minute Papers, Photonics, UploadVR, VRTimes, TechXplore, Hackaday, SIGGRAPH Blog, Immersive Pavilion BEST IN SHOW).
May 2018 - Jun 2018 Publicity for Instant 3D Photography (TechCrunch, Business Wire, F8 Conference keynote - 1:08:45).
Apr 2017 Publicity for Casual 3D Photography (Mark Zuckerberg keynote at F8 - 11:45, F8 day 2 keynote - 46:00).
Nov 2016 The Finnish Academic Association for Mathematics and Natural Sciences (MAL) prize for
the most distinguished Master's thesis (lehti.tek.fi/jarjesto/celebrating-academic-achievements).
Apr 2016 Rabin Ezra Scholarship for doctoral students in computer graphics, imaging and vision (rabinezra.info).

COMMITTEES AND REVIEWING

Area Chair / Papers Committee CVPR (2024), SIGGRAPH (2023, 2022), EGSR (2022, 2021, session chair), HPG (2024, 2021)
Reviewer SIGGRAPH, SIGGRAPH Asia, CVPR, ECCV, ICCV, TOG, TVCG, 3DV, Computers & Graphics, Eurographics, Pacific Graphics

EDUCATION

Aug 2014 - Jul 2019 PhD in Computer Science (University College London)
Viewpoint-Free Photography for Virtual Reality (discovery.ucl.ac.uk/id/eprint/10078087)
Supervisors: Gabriel Brostow and Tobias Ritschel.
Jan 2012 - Jun 2015 Master's degree in Computer Science (University of Helsinki)
Sequential Monte Carlo Instant Radiosity (helda.helsinki.fi/handle/10138/156669).
Sep 2009 - Jan 2012 Bachelors degree in Computer Science (University of Helsinki)
Triangle based and voxel based rendering in real-time graphics (phogzone.com/bscthesis.pdf - in Swedish).

TEACHING

2014, 2015, 2017 Teaching assistant, Computer Graphics (University College London)