Skip to content

← ArchivePaper2018

Avengers: Capturing Thanos's Complex Face

Darren Hendler, Lucio Moser, Rishabh Battulwar, David Corral, Phil Cramer, Ron Miller, Rickey Cloudsdale, Doug Roble

SIGGRAPHIndustrial11 citesFacial

Direct Drive retargeting system used on Thanos in Avengers, bypassing traditional blendshape solvers by learning a direct mapping from actor performance to character.

Abstract

In Marvel's Avengers: Infinity War, Thanos (played by actor Josh Brolin,) is entirely CG and is one of the the main characters in this live action movie. The plot depends on the emotional performances of this digital creature and it was imperative that Thanos's facial performance convey the actor's performances faithfully. Digital Domain's performance capture process, Direct Drive is a major departure from traditional blendshape solver techniques and was used to create Thanos's performances. We will present an overview of our updated multistage facial retargeting process. We have removed the reliance on high-resolution, per-shot facial capture and refined the process of training the system. This system is faster to set up, needs far less artist input, and preserves elements of the performance that were previously lost using traditional facial capture techniques.

How to read this

Category
Production talk: facial performance capture and retargeting
Contributions
  • Presents Digital Domain's Direct Drive retargeting used to drive the fully CG Thanos from the actor's performance
  • Departs from traditional blendshape solver techniques by learning a more direct actor-to-character mapping
  • Removes reliance on high-resolution per-shot facial capture, with faster setup, less artist input, and better preserved performance detail
Context
Builds on Digital Domain's head-mounted-camera capture work (Moser et al., Masquerade) and the broader move from blendshape-solver retargeting toward learned facial transfer.Builds on: Masquerade: Fine-Scale Details for Head-Mounted Camera Motion Capture Data
Correctness
Studio practice, not peer-reviewed; results are production-proven on a single hero character (Thanos), so reported speed and fidelity gains are tied to that specific pipeline and training setup.
Clarity
Accessible overview pitched at practitioners; a single read conveys the workflow without heavy math.
How to read it
Read for the high-level pipeline and how Direct Drive differs from blendshape solving; no second pass needed unless comparing facial-retargeting strategies.

Builds on

Built upon by

Nothing yet.

Related work

Keywords

This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →