Improving Videoconferencing With Realistic 3D Avatars: A New Way for Everyday Use

Evolution of Long-Distance Communication

Evolution of communication

Communication technology has evolved from letters to phone and video calls. Today, we are on the verge of the next breakthrough: Copresence technology that makes us feel like we are physically in the same room.

In a world where video conferencing is daily practice, the limitations of video calls are all too familiar to all of us. Many have experienced fatigueness when compared to natural conversations taking place in the real world, a phenomenon that stems from the lack of natural, non-verbal cues like establishing individual eye contact within group conversations as we as humans are used to do effectively in our daily life. These cues are essential for engaging, close and meaningful conversations, yet they’re totally missing in the flat, static world of conventional video conferencing until today.

A recent study (Gazing Heads: Investigating Gaze Perception in Video-Mediated Communication ) published at CHI, the largest scientific user experience conference, introduced a system that simulates head rotations based on eye gaze, enabling direct eye contact in virtual meetings on standard computer screens. The study, “Gazing Heads: Investigating Gaze Perception in Video-Mediated Communication,” found that participants felt more engaged, socially present, and connected compared to typical video conferencing. Researchers concluded that “Gazing Heads represents a clear advance over present-day video conferencing in its ability to convey gaze and attention.”

Gazing heads study The image above shows the participant feedback of the user’s that were subjects when comparing the “Gazing Heads” system to a traditional “Tiled View” the reader should be familiar with from his or her own user experience within today’s video conferencing environments.

  • More engaging/exciting: Over 80% of participants found Gazing Heads more engaging, with a small percentage preferring the Tiled View.
  • Perceived other’s attention: Approximately 80% of participants felt that Gazing Heads made it easier to perceive the attention of others.
  • Preferred for future use: Around 70% indicated a preference for using Gazing Heads in the future, while the rest were either undecided or favored the Tiled View.
  • More natural interaction: Roughly 70% of participants found interactions more natural with Gazing Heads.
  • More social interaction: About 70% preferred Gazing Heads for social interaction, with a minority showing no preference or favoring the Tiled View.
  • Suitability for persuading people: Around 50% found Gazing Heads suitable for persuasive discussions, while the other 50% were split between no preference and preferring the Tiled View.
  • Easier turn-taking: Approximately 70% of participants found Gazing Heads made turn-taking easier.

The video above shows this more natural video communication system fading between multiple cameras depending on each user’s gaze point determining who is looking at whom at every moment and leveraging this information to create a more immersive video conferencing experience for everyone. Though the system only took into account the user’s heads it is easily imaginable how the full experience by adding human bodies’ and atmospheric virtual 3D rooms could enhance the overall experience even more.

Note that this is a 4 person video call and that a self-view is not included as it is believed to have numerous negative distraction effects. Just as in the natural world you can also not see your-self while being in a conversation talking to others.

Green screen video conference The utilized system enabling this more natural video communication experience required a complex apparatus consisting of multiple cameras standing around each individual participant, making it impractical for the average user to acquire and set up at home and is therefore far away from being product ready.

But what if we could bring this enhanced experience to everyone, using technology that’s already in our pockets like a smartphone and a laptop or standard PC setup, what would you say?

Our Photorealistic 3D Avatars enable such a solution for the first time

With our photorealistic 3D avatars, this vision of significantly improving human interaction is on the verge of becoming an everyday reality. This breakthrough is only possible because our realistic avatars surpass the notorious uncanny valley effect, where subtle imperfections in digital human representations often create discomfort. Our technology, leading the world-wide market in terms of avatar quality, ensures that interactions feel genuine and lifelike, setting a new standard far beyond what competitors offer.

By making day-to-day conversations more natural and effective, our technology not only strengthens workforce productivity but also reduces the need for travel, especially for critical board meetings and intense discussions. This not only enhances efficiency but also contributes to saving environmental resources by minimizing unnecessary travel. Here’s how it would work:

  • Simple Avatar Creation with a Mobile App: Creating your lifelike 3D avatar using our 3D head scanning app which is using the high-quality camera on your smartphone to self-scan your face and create a detailed, photorealistic avatar looking just like you within just a few minutes. technically, you could also use your laptop camera, though mobile cameras typically offer superior image quality for this task nowadays and better usability.
  • Seamless Integration into Video Conferencing: Once your avatar is created, it could seamlessly integrate into your favorite video conferencing software. Instead of relying on your real-world appearance, your avatar looks just like you and represents you in the virtual meeting space. This avatar doesn’t just sit still—it dynamically rotates its head and adjusts its gaze, depending at which participant you are already looking on the monitor, when observed by the other video conferencing participants while you are actually looking on the screen in front of you and moving your eyes just slightly.
  • Real-Time Gaze Tracking: Gaze tracking powered by AI utilizes your laptop’s camera to estimate where you’re looking on the screen. Your 3D avatar mirrors these movements, simulating direct eye contact with other participants. This creates a more natural conversation flow, enhancing engagement and significantly reducing the cognitive strain often experienced during traditional video calls.
avatar conference avatar conference avatar conference avatar conference

Bringing Tomorrow’s Technology to Today’s Users

Our photorealistic 3D avatar solution has the potential to revolutionize video conferencing, making it more engaging and enjoyable—it’s about transforming the way we communicate in the digital age. At Copresence, we’ve crafted an experience that goes beyond traditional screens and static video, creating a level of co-presence that feels authentic and personal. Our advanced 3D avatar scanning technology enables high-fidelity digital representations that seamlessly adapt to users’ movements and expressions, ensuring interactions feel natural and connected.

With our technology, digital interactions are no longer limited by distance or equipment, redefining what virtual communication can be and setting a new standard for co-presence in our connected world. With our 3D Avatar scanning technology, the groundbreaking concepts explored in the Gazing Heads study are no longer confined to the lab—they’re almost ready for everyday use, making video conferencing more human, more connected, and more effective than ever before.