Dimensional Imaging Ltd (DI4D) is a world leading pioneer in the fields of facial capture and digital doubles. DI4D addresses the demand from leading international visual effects and video game companies for ever higher levels of graphical detail and realism in facial animation. Conventional methods of facial animation first require the creation of a "facial rig", comprising many "shapes" that represent different facial expressions. Facial animation is then achieved by activating different combinations of these shapes over time. Increasing the realism of facial animation requires the addition of exponentially more shapes, with ever more subtly different expressions. An increasing amount of manual animation "polish" is also normally required to produce more nuanced expressions. For over 20 years, DI4D has pioneered a novel alternative approach to facial animation using 4D capture and digital doubles (virtual characters that look exactly like a real-life person). The company's DI4D PRO system uses an array of synchronised high-resolution video cameras to capture the facial performance of an otherwise stationary actor. DI4D's advanced software is then used to reconstruct and track the 3D shape of the actors' face in every frame. The resulting 4D data can be used to directly drive the facial animation of a digital double, with a very high degree of fidelity and nuance -- and crucially without the need for any facial rig. The preferred method of facial performance capture for large scale entertainment applications is to use head mounted camera (HMC) systems that allow multiple actors to move and interact freely. With the assistance of a previous Innovate UK grant, DI4D has been able to develop its highly innovative PURE4D solution, which allows high fidelity 4D data to be derived from dual camera HMC footage. PURE4D uses machine learning to combine efficiently lower fidelity 4D data derived from the HMC performance with high fidelity 4D expression data of the actor captured with a DI4D PRO system. DI4D has achieved international commercial success by using PURE4D to deliver several hours of high-fidelity facial animation for the world's most demanding AAA video game projects, such as Activision's Call of Duty. This project will enable DI4D to continue to scale-up, innovate and compete commercially at a world leading level. The primary aim is to research and develop the means to produce 4D facial animation even more efficiently so that it can be used on a wider range of even larger scale entertainment projects.

Visual effects and video game companies are demanding ever higher levels of graphical detail and realism and are increasingly making use of motion capture to acquire animation from real life actors to such an extent that it is now one of the fastest growing industry sectors in the U.S. Creating increasingly realistic facial animation is particularly challenging because human perception is acutely tuned to facial appearance. Content developers are therefore demanding new and ever higher fidelity solutions for facial performance capture. In response, Dimensional Imaging has developed DI4D™, an extremely novel and innovative facial performance capture solution that can acquire very high fidelity data without requiring any special markers, make-up or structured light. DI4D™ is also uniquely amenable for use with helmet mounted camera (“HMC”) systems that are now industry standard. The main development goal of the project is to improve substantially the fidelity, efficiency and level of automation of the current DI4D™ solution by allowing more seconds of facial animation to be produced with an even higher level of fidelity and realism for substantially less manual effort.

Dimensional Imaging has developed a highly novel and proprietary facial performance capture solution (“DI4D™”) that requires no special markers, make-up or structured light. The current DI4D™ PRO system uses a bank of high resolution video cameras to capture the facial performance of a single performer who sits in front of the system. By capturing dense “3D scan” data at 60fps and then tracking a dense, fixed topology mesh through the resulting 3D scan sequence, the system provides many times the fidelity of traditional facial motion capture systems that track discrete dots. However, automatic pre-processing of the data currently requires approx. 20 minutes per second of captured data and manual post processing currently requires approx. 30 minutes per second of captured data. Under a previous InnovateUK funded Launchpad project, Dimensional Imaging has demonstrated the feasibility of using a head mounted camera (HMC) system to capture 4D facial performance capture data. This offers the benefits of more freedom of movement for the actors and the ability to allow multiple performers to be captured simultaneously. The aims of this project are 1) to develop a pre-production prototype HMC system, 2) test the prototype HMC in a “production” environment, 3) improve the efficiency of data processing stage (i.e. reduce significantly the time required to pre-process and post process 1 second of data), and 4) research the the most effective use of the captured performance data in facial animation pipelines. We believe that this will result in a world leading system that is capable of meeting the requirements of next generation video game development as well as VFX for television and movies

Dimensional Imaging has developed a highly novel and proprietary facial performance capture solution (“DI4D™”) that requires no special markers, make-up or structured light. By capturing dense “3D scan” data at 60fps and then tracking a fixed topology mesh through the resulting 3D scan sequence, the system provides much higher fidelity than traditional facial motion capture systems that track discrete dots. The current “sit down” system uses a bank of high resolution video cameras to capture a single performer who sits in front of the system and must keep their head and body relatively still. The aim of this project is to develop the system to use head mounted cameras wihc will allow more freedom of movement and allow multiple performers to be captured simultaneously. We believe that this will result in a world leading system that is capable of meeting the requirements of next generation video game development as well as VFX for television and movies.