Type of effects
DeepAR supports following types of effects:
Rigid objects are the basic type of effects that are supported by DeepAR SDK. It is a type of effect that is driven only by head position (translation, rotation, and scale) in 3D space. Typical effects in this category are glasses, hats, helmets and various other head accessories.
Deformable masks are the type of effects which, besides translation and rotation, are driven by facial expressions. Models are driven by the DeepAR reference head model in two ways - via vertices and bones. For more information see the Deformable masks section.
Morph mask are effects that allow transformations between two shapes, usually the basic reference head model and some desired shape. This is accomplished by creating a blend shape for the desired deformation out of the reference head model. That way the vertices/bones that drive the resulting model will be preserved. As a side effect to this, the transformation animation can be implemented - you can change the blend shape weight over time and user will see itself transformed into the desired effect/mask.
DeepAR SDK and Studio can load and display keyframe animations stored in fbx models. User can further edit the animations within DeepAR Studio and decide when and how the animations will be triggered and displayed. Read more in the sections on the model animations.
These are the typical image processing effects one can find in camera apps like simple black and white or sepia filter but include more complex ones like beauty filters. Post-processing effects are usually applied over the entire screen but can also be applied only on specific parts using render textures.