Christoph Lassner

Career

Lassner completed a PhD at the Bernstein Center for Computational Neuroscience and the Max Planck Institute for Intelligent Systems. Before joining Meta, Lassner worked at Body Labs, a startup later acquired by Amazon. Lassner created the human pose estimation system for Amazon Halo, part of a system for building a 3D body model with a smartphone.¹

Lassner later led research teams at Meta Reality Labs Research and at Epic Games. At Meta, the team's work on reconstructing and rendering radiance fields interactively was shown at Meta Connect 2022. Lassner is now a co-founder of World Labs, which names Lassner among its founders with Fei-Fei Li, Justin Johnson and Ben Mildenhall.¹²

Research and software

Lassner's research covers neural rendering and dynamic scene reconstruction, including Non-Rigid Neural Radiance Fields (2020) and Neural 3D Video Synthesis (2021), and human-focused work such as TAVA, ARCH and UP.³⁴¹

On the engineering side, Lassner wrote the Pulsar renderer in 2021, which became the sphere-based rendering backend for PyTorch3D, and received an Honorable Mention at the ACM Multimedia Open-Source Software Competition 2016 for work on decision forests.¹⁵

Work and contributions

• Pulsar: Efficient Sphere-based Neural Rendering Open-source code

  First author, with Michael Zollhöfer, of the Pulsar paper; Lassner wrote the Pulsar renderer, which is now the sphere-based rendering backend for PyTorch3D.⁵¹

• Neural 3D Video Synthesis from Multi-view Video Published research

  Co-author of the 2021 paper on synthesizing dynamic 3D video from multi-view captures, one of the works Lassner's site lists on rendering representations of the physical world.⁴¹

Timeline

1. 2016Received an Honorable Mention at the ACM Multimedia Open-Source Software Competition for decision forest software.¹
2. Apr 2020Posted the Pulsar paper on efficient sphere-based neural rendering as first author.⁵
3. Dec 2020Co-authored Non-Rigid Neural Radiance Fields for dynamic scenes from monocular video.³
4. Mar 2021Co-authored Neural 3D Video Synthesis from Multi-view Video.⁴
5. 2022The Meta research team's interactive radiance field work was featured at Meta Connect 2022.¹

Other documented roles

Roles the sources document that are not confirmed as current.

• Research team lead, Meta Reality Labs Research¹
• Research team lead, Epic Games¹
• Worked at the startup, which Amazon later acquired, Body Labs¹

Honors and recognition

• ACM Multimedia Open-Source Software Competition, Honorable Mention · ACM Multimedia, 2016¹

Where they work

• World Labs 4 people in the wiki

Related people

• Ben MildenhallAlso at World Labs
• Justin JohnsonAlso at World Labs
• Fei-Fei LiAlso at World Labs
• David ForsythComputer vision · Image, video, and 3D generation
• Phillip IsolaComputer vision · Image, video, and 3D generation
• Bilawal SidhuImage, video, and 3D generation · Computer vision
• Alex NicholImage, video, and 3D generation · Computer vision
• Tsung-Yi LinComputer vision · Image, video, and 3D generation
• David LuebkeImage, video, and 3D generation · Computer vision
• Alexei A. EfrosComputer vision · Image, video, and 3D generation