A quick reminder of the importance of a solid calibration to support best results. Below is some specific advice on what to do. There are smart updates in the works to make all of this easier (more detail to follow in the next few weeks).  

 

Summary (tl;dr): 

 

  • Do this: make sure the actor starts the scene, from the first frame onwards, in a T-pose facing, and in full view of, the camera, at the center of the scene (stage), with the entirety of the body visible and feet firmly planted on the floor, for 1 – 2 seconds.  
  • Don’t do this: we mean “starting” your scene with a T-pose literally. Avoid footage prior to the T-pose or N-pose in which the actor prepares for the scene. This includes the actor “transitioning” into the T-pose, such as walking into the frame, standing in profile, turned away from the camera, or otherwise anything less than a solid T-pose. Trim (edit) those frames out of the video, if you can.  

 

RADiCAL Core calibration:

 

We currently accept, without warning, videos in which the actor’s presence is visible enough, but falls short of a solid T-pose. We made that decision because many of our users would prefer to have some results, rather than no results at all. However, this also means that we currently don’t warn users when their calibration wasn’t supportive of best results. 

 

Therefore, you should carefully review how your video starts: if there is a solid T-pose in the video, great. If there’s no T-pose, try to find a natural, full-body camera-facing pose that comes close to it. Either way, try to trim away (edit out) any footage that comes before it. 

 

RADiCAL Studio calibration:

 

  • Step-by-step (SbS) processing: The Studio app already comes with a mandatory five-second countdown to assist you in finding the best position before the Studio app starts recording your video for SbS processing. Make sure the actor stands in a solid T pose by the time the Studio app has completed the countdown and starts recording.
  • Real-time (RT) processing: Because there is no five second countdown, you‘ll need a person other than the actor to hit the START button. You can also experiment with external camera integrations (to ensure a better angle and distance) or keyboards / mouse configurations (to allow for remote operation of the Studio app). 

We’ve released plugins to make the re-targeting process faster and easier for Blender and Unreal users.

For our Studio customers, we have deployed a dedicated FBX exporter through our website: https://getrad.co/uploader-studio.  

Note that the Studio FBX exporter will only read animation data produced by RADiCAL Studio. You need an active Studio subscription to use the Studio FBX exporter.

For more information on how it works, check out the dedicated learn section for RADiCAL Studio.

Studio’s real time functionality opens up exciting possibilities for previz and virtual production.  For virtual production professionals and enthusiasts, we are enabling Unreal Engine 4 LiveLink access with RADiCAL Studio. We’ve described how it works in detail here (FAQs).

We have included a sample Unreal project and instructions on setting it up with Studio.  It’s available through this Github repo.

Professional Studio subscribers will have livestream access to all engines included in their subscription.

We are also developing livestreaming capabilites for Unity, Blender, and iClone.

Our latest AI: Gen3 

 

Today, we are launching Gen3, the latest generation of our AI for our community of creators and developers. 

 

Gen3 has been a labor of love, skill and persistence. We’ve been on it for more than a year, because we knew that the Gen3 architecture would lay the foundation for a revolution in 3D motion tracking science. It is difficult to overstate how excited we are.  Not only does Gen3 provide far improved output, it also does so at significantly enhanced throughput.  So much so, that it’s now capable of being run in real time.  

 

With all those improvements now available, we’ll be releasing a range of new products, both in the cloud and for local (on prem) use.

 

RADiCAL consists of a small team of 3D graphics and AI enthusiasts.  We hope you enjoy the fruit of our labor as much as we do.  Below we have summarized just some of the highlights we want you to know about. 

 

Key features: 

 

RADiCAL is optimized for content creators, with the following priorities guiding everything we do: 

 

  1. Human aesthetics: because of our holistic approach to motion and deep learning, we’ve massively enhanced the human, organically expressive look and feel of our output, with smooth results that substantially reduce jitter and snapping; 
  2. Fidelity: Gen3 was designed to tease out much more detail in human motion than previous versions; 
  3. Speed: we want to ensure that our technology is capable of running in real time across most hardware and software environments. 

 

Going forward, Gen3 will support both CORE (our cloud-based motion capture technology) and new real time products (including an SDK) that we will announce and release shortly.  

 

While Gen3 has moved in massive leaps toward realizing those priorities, we also know that we have more work to do. More about that below. 

 

About our science:

 

There’s a lot of secret sauce in our science. But here’s what we can say: we’ve developed our AI to understand human motion holistically. Rather than creating a sequence of poses to create the impression of motion, we interpret the actor’s input through an understanding of human motion and biomechanics in three-dimensional space over time. In other words, our technology thinks in four dimensions: x, y, z and time.

 

We have more work to do:

 

As proud as we are of our progress, we want to do better in a few areas. One of our top priorities for the next few weeks and months is to better anchor our animations to the floor and reduce certain oscillations. 

 

We expect to roll out a first set of improvements within weeks, which should take us much closer to where we want to be in terms of reducing foot sliding  and oscillations. 

 

But we expect more work to be necessary after that. Those additional improvements will come with the next large release, in version 3.1 or 3.2.  We’ve already started to work on those improvements and we’re genuinely excited about making the results of our research public soon.

 

In the meantime, you can substantially mitigate these effects by following the guidance below.

 

How to get the best results:

 

To get the most out of our technology, you should: 

 

  • Static, stable camera: place your camera on a flat, stable surface (or a tripod, of course). Don’t adjust the zoom while recording. Don’t cut between different camera angles. 
  • Single actor: record a single person at a time; 
  • T-pose calibration:  ensure the actor strikes a T pose within the first five seconds with the entire body being clearly visible at a frontal angle to the camera; and 
  • Aspect ratio: record, use or upload videos with aspect ratios not wider than 4:3.  That’s because our AI only processes videos in a 4:3 ratio. While you can upload videos with wider ratios (we’ll crop them back automatically), you should keep your actor inside the 4:3 ratio to ensure they don’t get cropped out.    

 

Play nicely, and you’ll get best results!

 

* *

 

As ever, we’re forever grateful for the support of the RADiCAL community.  We’re excited about feedback, good and bad.  We’re even more excited about constructive criticism and assistance.  

– Team RADiCAL 

We’re excited to announce that the very talented CG Geek has released an easy-to-follow tutorial on how to use RADiCAL to animate characters in Blender.

In this video, Steve takes you through the entire process from start to finish on how to animate characters using RADiCAL FBX output in Blender.  He starts out by filming the scene, mapping the character, retargeting the animation, as well as rendering the character.

Steve’s video (and many more that are great) can be seen here on his YouTube channel.

Steve’s video comes on the heels of massive improvements in our product.  With our impending Gen3 release, we will be releasing a much improved skeleton with plugins for Unity, Unreal, and Blender.

For our Blender users, we are now also releasing a standard T-pose rig that will make the re-targeting process easier. You can currently download the t-pose file here, and it will soon be available through our download page as well.  Steve describes how to use the T-pose rig in his video.

Also, as a reminder, if you’d like to share your animated characters with us, we’ll post and promote your content on our social media channels.  Be in touch!

 

*          *          *

-Enjoy!

Team RADiCAL