It may soon become difficult to tell the difference between virtual reality and reality. On the second day of Facebook’s annual F8 conference, the company announced it is closer to making “AR/VR experiences feel like reality”.
• F8 Conference Day 1: Privacy update, Oculus Go + Facebook dating?
To prove this, the social media giant has released a video that shows a side-by-side comparison of normal footage of a living room space with its 3D reconstruction. The resemblance of the two footages is uncanny.
Facebook says its work in the AR/VR space is a part of its mission to connect people. It will help “create better shared experiences, regardless of physical distance”, the tech giant said in a blog post.
While day one of the F8 conference was about sharing details of tools and updates coming to Facebook-owned platforms, the second day was focused on the company’s long-term investment in AR/VR, connectivity and artificial intelligence.
Here are Facebook’s highlights from day two of the F8 conference:
AR/VR
• Facebook’s advancements in AR and VR draw from an array of research areas to help us create better shared experiences, regardless of physical distance. From capturing realistic-looking surroundings to producing next-generation avatars, we’re closer to making AR/VR experiences feel like reality.
Our research scientists have created a prototype system that can generate 3D reconstructions of physical spaces with surprisingly convincing results. It’s hard to tell the difference. Realistic surroundings are important for creating more immersive AR/VR, but so are realistic avatars. Our teams have been working on state-of-the-art research to help computers generate photorealistic avatars.
Artificial Intelligence
• Today at F8, our artificial intelligence research and engineering teams shared a recent breakthrough: the teams successfully trained an image recognition system on a data set of 3.5 billion publicly available photos, using the hashtags on those photos in place of human annotations. This new technique will allow our researchers to scale their work much more quickly and they’ve already used it to score a record-high 85.4% accuracy on the widely used ImageNet benchmark. We’ve already been able to leverage this work in production to improve our ability to identify content that violates our policies.
• This image recognition work is powered by our AI research and production tools: PyTorch, Caffe2, and ONNX. Today, we announced the next version of our open source AI framework, PyTorch 1.0, which combines the capabilities of all these tools to provide everyone in the AI research community with a fast, seamless path for building a broad range of AI projects. The technology in PyTorch 1.0 is already being used at scale, including performing nearly six billion text translations per day for the 48 most commonly used languages on Facebook. In VR, these tools have helped in deploying new research into production to make avatars move more realistically.
• The PyTorch 1.0 toolkit will be available in beta within the next few months, making Facebook’s state-of-the-art AI research tools available to everyone. With it, developers can take advantage of computer vision advances like DensePose, which can put a full polygonal mesh overlay on people as they move through a scene – something that will help make AR camera applications more compelling.
Connectivity
Advancements in AI and AR/VR are relevant only if you have access to a strong internet connection. There are currently 3.8 billion people around the world who don’t have internet access.
• To increase connectivity around the world, we’re focused on developing next-generation technologies that can help bring the cost of connectivity down to reach the unconnected and increase capacity and performance for everyone else. In Uganda, we partnered with local operators to bring new fibre to the region that, when completed, will provide backhaul connectivity covering more than 3 million people and enable future cross-border connectivity to neighbouring countries. Meanwhile, Facebook and City of San Jose employees have begun testing an advanced Wi-Fi network supported by Terragraph.
Trials of Terragraph are also planned for Hungary and Malaysia. We are also working with hundreds of partners in the Telecom Infra Project to build and launch a variety of innovative, efficient network infrastructure solutions. And, as with our work in AI and other areas, we are sharing what we learn about connectivity so that others can benefit from it.
—
Top photo: Facebook’s Chief Technology Officer Mike Schroepfer talking about AR:VR, connectivity and AI at F8