Manifold Valley unveils tech for realistic digital humans

Manifold Valley, an AI and machine learning start-up, has developed advanced technology that enables the creation of hyper-realistic digital humans for use in triple-A video games.

Ian Bloom, Founder and CEO of Manifold Valley, shared insights into his company's technological advancements, which blend his background in cinematography and programming. Bloom explained his journey, stating, "I started programming at age seven. That happened because my older brother went to computer camp and came home and taught me to make simple games in BASIC. My goal as a kid was to make games like Castle Wolfenstein and Quake and to program like John Carmack, the Co-Founder of id Software."

Bloom's interest in technology was nurtured by his family, which ran an engineering start-up from their home. "My parents ran an engineering startup from our house, Dad performed the technical work and Mom secured the contracts... As kids we had access to CAD workstations and all types of fabrication tools," Bloom recalled.

The development of Manifold Valley's technology has transitioned Bloom from cinematography to machine learning. "After earning a Film Production degree in North Carolina, I moved to New York where I immersed myself in various roles from Gaffer to Digital Imaging Technician, and eventually as Director of Photography on many projects," he detailed.

From this diverse experience, Bloom realised the importance of human emotion in film, asserting that "no amount of cinematography tricks or technology can make a movie exceptional." He added, "Her [Breeda Wool] portrayal of this character was so raw and in-the-moment that I had this epiphany where I realised my job is to just get out of this person's way." This understanding has heavily influenced his approach to machine learning-based performance capture.

Manifold Valley's technology, termed 'performance reproduction,' aims to enhance actors' natural performances without restrictive equipment. "Traditional motion capture methods often hinder actors, forcing them into restrictive suits and equipment that disrupt their creative process," Bloom explained. "There's so many additional steps in the process and quality loss which means what's taking place in the studio is not guaranteed to be transmitted into the game. "

Bloom highlighted the potential of this technology to replicate a theatre stage environment, allowing performers to act naturally. "Exactly right. When Emmanuel Wazar, our Animation Specialist joined Manifold Valley, he was the first to harness the tech in an artistic manner," he stated.

In terms of its impact on video games, Bloom noted the current industry prioritises gaming mechanics over human interactions. "A lot of what we see in games today is shaped by the economics of including digital human characters," he said, suggesting this could change with Manifold Valley's technology by elevating the cultural significance of video games.

Bloom envisions Manifold Valley's technology bringing greater emotional engagement in gaming. "We find it brings deeper storytelling by creating characters which emotionally connect with gamers," he said. The system, he claims, could be applied to both humanoid characters and fantasy creatures.

On the future of AI-driven performance capture, Bloom believes that, "AI-driven technologies like Manifold will revolutionise digital human creation, offering game studios, filmmakers and content creators unprecedented control and efficiency in producing compelling narratives and life-like characters."

Bloom concluded by expressing confidence in the balance between large generative models and targeted specialisation. "Most companies in the artificial intelligence and machine learning space are building or using huge one-size-fits-all models."

"What differentiates us is the fact we efficiently specialise in smaller models which does exactly what you need as a creative tool," he said. "I'm so excited about the creative potential in ways artists will use our technology for!"