We're launching photorealistic Neural Radiance Fields (NeRFs) at Mapillary

Today, Mapillary is launching NeRFs, a new feature that will allow you to explore landmarks and popular sites in detailed 3D views – all reconstructed from 2D images uploaded to Mapillary.
Peter Kontschieder
14 Mar 2024

Starting today, Mapillary is offering Neural Radiance Field (NeRF) reconstruction support as a new feature. But hold on – what exactly are NeRFs?

Neural Radiance Fields, or NeRFs, are a relatively new type of 3D model that can be generated from a set of 2D images for a scene. The technology works by using machine learning algorithms to analyze the images and create a 3D representation of it. This allows for incredibly detailed and realistic reconstructions of real-world scenes, capturing everything from the intricate details of buildings to the lush foliage of trees, including view-dependent effects. But that's not all - once trained, NeRFs can be used for novel view synthesis, allowing us to render a video from any angle and camera trajectory. This means that it is possible for us to navigate around in the 3D model as if we were actually there, giving us a completely new way to experience and explore the world. Whether you're interested in exploring new places or just want to see your local neighborhood in a whole new light, our NeRF reconstructions are a powerful tool for mapping enthusiasts everywhere.

By making NeRFs available on Mapillary, we’ve enabled completely new options for mapping landmarks and popular sites worldwide. Imagine being able to observe places like the Swiss National Museum in stunning three-dimensional detail, just by visiting Mapillary. This technology allows us to capture and recreate some of the most iconic locations on Earth in a way that was previously impossible. We have generated a few high-quality NeRF renderings from street-level data that have already been uploaded to our platform – these reconstructions showcase the incredible level of detail that NeRFs can achieve, and we can't wait for your feedback.

Of course, we also want to encourage all our users to get involved and capture their own preferred places to populate our maps with even more amazing NeRF reconstructions. That's why we have instructions available on how to capture the data in the best possible way. We’re excited to see what our community creates. Whether you're interested in capturing your local park or a famous landmark, we're here to help every step of the way.

So what are you waiting for? Get out there and start capturing!
/Peter