Revolutionizing Gaming: AI Creates Hyperrealistic Digital Humans
The video game industry is on the cusp of a revolution. Manifold Valley, a cutting-edge AI and machine learning startup, has developed technology capable of creating hyperrealistic digital humans for AAA video games, promising a level of emotional depth and realism never before seen.
ian Bloom, Founder and CEO of Manifold Valley, credits his unique background in both cinematography and programming for the company’s breakthrough. “I started programming at age seven,” Bloom recalls. “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 passion for technology was nurtured in a family environment steeped in innovation. “My parents ran an engineering startup from our house,” he explains. “Dad performed the technical work and Mom secured the contracts… As kids we had access to CAD workstations and all types of fabrication tools.” This early exposure laid the groundwork for his future endeavors.
Bloom’s journey from cinematography to machine learning is a testament to his adaptability. ”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 details. This experience profoundly shaped his understanding of human emotion on screen.
Bloom emphasizes the crucial role of genuine human emotion in filmmaking. “No amount of cinematography tricks or technology can make a movie exceptional,” he asserts. He further explains, referencing a pivotal moment in his career, “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 ideology underpins Manifold Valley’s approach to machine learning-based performance capture.
Manifold Valley’s “performance reproduction” technology aims to capture the nuances of actors’ performances without the constraints of conventional motion capture. “Traditional motion capture methods often hinder actors, forcing them into restrictive suits and equipment that disrupt their creative process,” Bloom explains. ”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 envisions a future where actors can perform naturally, mirroring the freedom of a theatrical stage. “Exactly right,” he confirms. “When Emmanuel Wazar, our Animation Specialist joined Manifold Valley, he was the first to harness the tech in an artistic manner.” This approach promises to unlock a new level of authenticity in digital characters.
bloom points out a critical gap in the current gaming landscape: the prioritization of mechanics over human interaction.”A lot of what we see in games today is shaped by the economics of including digital human characters,” he observes. Manifold Valley’s technology, he believes, has the potential to shift this paradigm, elevating the cultural significance of video games.
The potential impact on gaming is meaningful. “We find it brings deeper storytelling by creating characters which emotionally connect with gamers,” Bloom says, emphasizing the technology’s ability to foster deeper emotional engagement. He also notes the system’s adaptability,applicable to both humanoid characters and fantastical creatures.
Looking ahead, Bloom is optimistic about the future of AI-driven performance capture. “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,” he predicts.
Bloom concludes by highlighting Manifold Valley’s unique approach to AI model progress. “Most companies in the artificial intelligence and machine learning space are building or using huge one-size-fits-all models,” he explains. “What differentiates us is the fact we efficiently specialise in smaller models which does exactly what you need as a creative tool,” he adds. “I’m so excited about the creative potential in ways artists will use our technology for!”
