gen‑ai.news
← Back
Multimodal

Tom Hanks Played Five Characters in This 2004 Christmas Movie

Tom Hanks Played Five Characters in This 2004 Christmas Movie

When The Polar Express arrived in 2004, most audiences noticed that the conductor looked a lot like Tom Hanks. Fewer noticed that Hanks was also the hobo riding atop the train, the boy's father, Santa Claus, and the film's narrator - six roles in total, though he is typically credited with five. The choice was not purely a novelty: Hanks explained in press interviews at the time that every adult figure in the story could be understood as a projection of the young lead character's inner world, each one a variation on the people he trusted and wondered about. Santa, in particular, had to be physically imposing in the boy's imagination - not a soft, familiar figure but someone large enough to actually lift a sack of presents.

Robert Zemeckis shot the film using performance capture, a process he distinguished from standard motion capture. Actors wore up to 150 small reflectors across their bodies, and the first unit focused entirely on performance - lighting and virtual camerawork were handled separately in post-production by cinematographers Don Burgess and Rob Presley, who operated virtual cameras during the editing phase. VFX supervisor Jerome Chen noted that Zemeckis approached the whole production as though he were directing a live-action film rather than an animated one. Scenes involving Hanks alongside child characters were captured twice - once with child stand-ins and once with adult actors - giving Zemeckis the ability to combine the best body performance with the best facial performance independently.

Zemeckis had briefly considered having Hanks play every single role in the film. Hanks himself put a stop to that idea after a test day in which he moved through five, six, or seven characters in quick succession and found it genuinely exhausting. He settled on the five he could keep clearly distinct in his head. That ceiling is worth noting for any filmmaker working with actors in demanding multi-role situations - even when technology removes physical restrictions, cognitive and emotional load remains real.

Hanks was openly enthusiastic about where performance capture might lead. He told the Los Angeles Times that the technology made height, hair color, gender, and even race irrelevant to casting, opening possibilities that traditional production could not offer. Zemeckis went on to apply the same approach to Beowulf in 2007 and A Christmas Carol in 2009, and later used related de-aging techniques in Here. The Polar Express stands as an early, still-visible example of what happens when a director treats performance capture as a creative tool rather than simply a production shortcut.

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

What Is MAX Sneaks? Your First Look at Tools That Don’t Exist Yet
Multimodal

What Is MAX Sneaks? Your First Look at Tools That Don’t Exist Yet

Adobe MAX Sneaks is an annual event where Adobe researchers demo experimental technology that has not yet made it into any product. Some of these demos eventually become familiar tools in Premiere, After Effects, or Photoshop - others never ship at all. This year's Sneaks airs Wednesday, November 11, and is free to watch online.

Adobe’s AI experiments let you walk around in photos and interview your characters
Multimodal

Adobe’s AI experiments let you walk around in photos and interview your characters

Adobe's annual Max conference has brought a fresh batch of experimental features, including tools that convert flat photos into navigable 3D scenes, let creators shape AI characters through conversation, and simplify photo editing to a copy-and-paste workflow. These "Sneaks" projects offer a glimpse into where Adobe's generative AI research is heading. None are shipping products yet, but they reflect the direction of the company's broader creative toolset.

Introducing the Multimodal Knowledge Agent benchmark
Multimodal

Introducing the Multimodal Knowledge Agent benchmark

Google has introduced the Multimodal Knowledge Agent (MKA) benchmark, a new evaluation framework designed to test how AI agents reason through visually complex, multimodal tasks. Unlike simpler benchmarks, MKA focuses on the kind of layered reasoning required when an agent must draw on both visual and textual information simultaneously. The release signals growing interest in more rigorous, real-world testing standards for multimodal AI systems.