We’ve just released Scene360 for scene classification of 360° images. Usage is currently free so you’re just one button click away from deploying the model on AWS and classifying 360° images within your own apps or pipelines.

Many traditional image classification systems target images of specific objects or narrow views. For 360° images an entire panoramic view is captured and the question of interest is often to classify the entire scene of the image. Scene360 provides meaningful full panoramic scene classification for precisely this task.

Check out the examples below!

For each scene we list the most likely category, as well as few other probable but slightly less likely categories (ordered by likelihood). Additionally, the mode can immediately check whether a scene is indoors or outdoors, and to measure the presence or absence of a hundred semantic attributes, e.g. the existence of a horizon in the image, of folliage, natural light.

categories: beach, ocean, coast, tundra, lagoon
attributes: open area, natural light, faraway horizon, natural
location: outdoors

categories: artist’s loft, art gallery, alcove, art studio, closet
attributes: enclosed area, no horizon, man made
location: indoors

categories: television room, bedroom, alcove, hotel room, living room
attributes: enclosed area, no horizon, man made
location: indoors

What is more, we can explore why the model believes an image is well characterized by a given scene by creating attention heatmaps that show the most important regions of the scene that are driving predictions.

In the following images, the model is looking for a “forest path”. The center of attention clearly identifies the path and the root systems of the trees:

Forrest path

Attention heatmap of forrest path

You can access our Scene360 model on the AWS marketplace here.