On this page I can read:
Live camera video texture-mapped onto the ARKit face mesh, with which you can create effects that appear to distort the user’s real face in 3D.
I haven't found much sample and extra documentation about this.
Is it possible to distort the face itself in 3D with ARKit? Like changing chin shape and such?
If yes, briefly on a conceptual level, how could this be achieved?
You shouldn't distort the canonical mesh used by Metal (ARSCNFaceGeometry). However, if you intend to dynamically distort a facial mask, you have two options:
create an animated face model in 3D authoring app
use SceneKit's SCNMorpher with its morph targets
Related
Via ARKit, I want to place indoor map on floor.
Currently I tried 2 things:
I've placed large Plane below camera and above floor, But it causes quite drift. Does not move well when we walk, and overall experience is not overwhelming.
Saw a solution where you can identify horizontal plane, but it has its own issues.
So is it really possible with good results?
Devices with LiDAR
The LiDAR scanner has its advantages and disadvantages. The main advantage of LiDAR is its ability to almost instantly reconstruct floor and walls, then you can easily attach any 3D model to the resulted surface – a model will be stable, it will not drift, so a user's AR experience will be overwhelming, as you said. Also, an important advantage of LiDAR is the excellent performance in environment with poor lighting and with poor textures.
Here you can read about Occlusion feature and some of the LiDAR peculiarities. Good news: LiDAR perfectly works in conjunction with the Plane Detection option.
ARKit subdivides the reconstructed scene into ARMeshAnchors which give you access to polygonal geometry and surface classification.
ARMeshAnchor().geometry.classification
ARMeshAnchor().geometry.faces
ARMeshAnchor().geometry.vertices
ARMeshAnchor().transform.columns.3
Devices without LiDAR
In the absence of a LiDAR scanner, we can only detect horizontal and vertical surfaces using the Plane Detection feature. I can say that all AR frameworks (including ARKit and RealityKit) are much better and faster in defining horizontal surfaces, as opposed to vertical ones.
However, Detected Planes are less stable compared to Reconstructed Surfaces, and therefore, a slight drifting is possible sometimes. To successfully complete the Plane Detection stage, you need a well-lit room and good-for-tracking surrounding objects' textures.
ARKit calls your delegate's renderer(_:didAdd:for:) with a ARPlaneAnchor for each unique vertical and/or horizontal surface. And each plane anchor provides details about the surface – its world position, dimensions and real-world surfaces' classification.
In addition to the above, the delegate method called renderer(_:didUpdate:for:) is required to merge multiple coplanar Detected Planes into bigger resulting Detected Plane (a surface of a floor, for example).
ARPlaneAnchor().classification
ARPlaneAnchor().extent
ARPlaneAnchor().alignment
ARPlaneAnchor().center
Is it really possible with good results?
Yes, in both cases, it's possible to attach a map without drifting – whether you're using Plane Detection or Scene Reconstruction.
I have faced the issue of real face detection using Vision Framework.
I have referred below apple link.
https://developer.apple.com/documentation/vision/tracking_the_user_s_face_in_real_time
I used demo code provided in above link. I see, Camera can detect the face from printed photo or passport photo. It is not real face photo. How can I know if this is not real face in camera using Vision framework?
You can use https://developer.apple.com/documentation/arkit/arfacegeometry
This will create a 3D mesh of a human face. A 3D mesh will have different values (e.g. vertices , triangleIndices), in its topology compared to a 2D picture.
Here is a project link
here I have used camera API for face detection and eye blinking. you can check and customize according to your requirement.
Update: Here is another project for liveness Check using MLKit link
Vision + RealityKit
Apple Vision framework has been processing "2D requests". It works only with RGB channels. If you need to process 3D surfaces you have to implement LiDAR scanner API, that based on Depth principles. It will allow you to distinguish between a photo and a real face. I think that Vision + RealityKit is the best choice for you, because you can detect a face (2D or 3D) at first stage in Vision, and then using LiDAR, it's quite easy to find out whether normals of polygonal faces are directed in the same direction (2D surface), or in different directions (3D head).
At Google I/O'19 for Augmenting Faces and Images, they said about reference_face_texture.PNG for painting or apply texture to specific areas in a face for example lips, cheeks etc. but i am unable to find this reference face texture, so that i can use it in Photoshop to apply textures to exact area i want to apply, and then apply the new created texture using the face tracker in augmented-faces arcore. Can somebody please highlight it. Thank you.
i did tried downloading facial mesh images from online, but it is not perfect match after applying the textures to mesh image.
I could not find reference_face_texture as well, but you can open a reference 3D model and make a UV texture. To save you time: here is the texture
I’ve read this article http://www.gamasutra.com/blogs/BrianKehrer/20160125/264161/VR_Distortion_Correction_using_Vertex_Displacement.php
about distortion correction with vertex displacement in VR. Moreover, there are some words about other ways of distortion correction. I use unity for my experiments(and try to modify fibrum sdk, but it does not matter in my question because I only want to understand how these methods work in general).
As I mentioned there are three ways of doing this correction:
Using Pixel-based shader.
Projecting the render target onto a warped mesh - and rendering the final output to the screen.
Vertex displacement method
I understand how the pixel-based shader works. However, I don’t understand others.
The first question is about projection render target onto a warped mesh. As I understand, I should firstly render image from game cameras to 2(for each eye) tessellated quads, then apply shader with correction to this quads and then draw quads in front of main camera. But I’m afraid, I’m wrong.
The second one is about vertex displacement. Should I simply apply shader(that translate vertex coordinates of every object from world-space into inverse-lens distorted & screenspace(lens space)) to camera?
p.s. Sorry for my terrible English, I just want to understand how it works.
For the third method (vertex displacement), yes. That's exactly what you do. However, you must be careful because this is a non-linear transformation, and it won't be properly interpolated between vertices. You need your meshes to be reasonably tessellated for this technique to work properly. Otherwiese, long edges may be displayed as distorted curves, and you can potentially have z-fighting issues too. Here you can see a good description of the technique.
For the warped distortion mesh, this is how it goes. You render the screen, without distortion, to a render texture. Usually, this texture is bigger than your real screen resolution to compensate for effects of distortion on the apparent resolution. Then you create a tessellated quad, distort its vertices, and render it to screen using the texture. Since these vertices are distorted, it will distort your image.
We are trying to achieve the following in an iphone game:
Using 2d png files, set-up a scene that seems 3d. As the user moves the device, the individual png files would warp/distort accordingly to give the effect of depth.
example of a scene: an empty room, 5 walls and a chair in the middle. = 6 png files layered.
We have successfully accomplished this using native functions like skew and scale. By applying transformations to the various walls and the chair, as the device is tilted moved, the walls would skew/scale/translate . However, the problem is since we are using 6 png files, the edges dont meet as we move the device. We need a new solution using a real engine.
Question:
we are thinking of instead of applying skew/scale transformations, that if given the freedom to move the vertices of the rectangular images, we could precisly distort images and keep all the edges 100% aligned.
What is the best framework to do this in the LEAST amount of time? Are we going about this the correct way?
You should be able to achieve this effect (at least in regards to the perspective being applied to the walls) using Core Animation layers and appropriate 3-D transforms.
A good example of constructing a scene like this can be found in the example John Blackburn provides here. He shows how to set up layers to represent the walls in a maze by applying the appropriate rotation and translation to them, then gives the scene perspective by using the trick of altering the m34 component of the CATransform3D for the scene.
I'm not sure how well your flat chair would look using something like this, but certainly you can get your walls to have a nice perspective to them. Using layers and Core Animation would let you pull off what you want using far less code than implementing this using OpenGL ES.
Altering the camera angle is as simple as rotating the scene in response to shifts in the orientation of the device.
If you're going to the effort of warping textures as they would be warped in a 3D scene, then why not let the graphics hardware do the hard work for you by mapping the textures to 3D polygons, then changing your projection or moving polygons around?
I doubt you could do it faster by restricting yourself to 2D transformations --- the hardware is geared up to do 3x3 (well, 4x4 homogenous) matrix multiplication.