Interview of a 3D rigging supervisor

How to be a great 3D Rigger? A Conversation with Eisko’s Rigging Supervisor

by Non classé
In our ongoing pursuit of exploring the exciting world of 3D modeling and character creation, we had the pleasure of sitting down with Romain Astolfi, the rigging supervisor at Eisko and Polywink, your trusted partner in the realm of 3D. In this exclusive interview, we dive deep into the nuances of 3D rigging, the challenges faced, and the vision for the future. Join us as we gain unique insights and inspiration from Eisko’s rigging supervisor, providing a behind-the-scenes glimpse into the captivating world of rigging.

How would you define 3D rigging?

Rigging in the context of 3D refers to the process of adding bones and physics to a static 3D model in order to enable movement and animation. It is an essential component in 3D pipelines.

How do you become a rigger?

Becoming a rigger requires a solid understanding of various aspects of 3D. Knowledge of modeling, re-topology techniques, and character anatomy is crucial. Additionally, familiarity with animation is important, as rigging involves adapting the character’s rig based on the animation requirements. To embark on a career as a rigger, it is advisable to first gain a comprehensive understanding of 3D through general classes before deciding to specialize.

How do you maintain your passion for rigging?

I am deeply passionate about rigging because I enjoy solving puzzles, and each rig I work on presents a unique challenge. The process of unraveling these mysteries is the aspect of my job that I enjoy the most.

How do you determine if a project is a great one?

I recall a production experience where we received numerous characters from a client. Initially, we were impressed by the volume of work. However, it turned out that the characters were all part of a TV series, and the client informed us that we had rigged all the 3D models. This revelation made us immensely proud, and it fostered a great interaction with the client. This demonstrates that a successful project can be determined by factors such as client satisfaction and the positive impact the work has on the overall production.

How do you envision the future of 3D rigging and digital humans?

The future of rigging is likely to involve automation to a certain extent. Creating tools and scripts to streamline rigging processes will become an integral part of the job. Although rigging will undergo changes, I am not concerned about its future. As for digital humans, I am excited by the fact that it is attracting a wider audience, including those who were not previously involved in 3D. The growing interest in 3D and character creation indicates a promising future for the field.

How would you advise a 3D rigging beginners?

As mentioned earlier, it is essential to acquire a strong foundation in 3D before specializing in rigging. Taking classes, particularly in 3D schools, can provide a comprehensive education and ensure a solid base of knowledge. Starting with a general understanding of 3D artistry for a couple of years before focusing on rigging will help beginners feel more comfortable and well-prepared.

How do you approach challenges in your work?

Working at Eisko presents us with a multitude of new challenges, which I find stimulating. Our policy is to maintain the highest quality standards for all the 3D models we work on, regardless of whether we created them or received them from a client. This necessitates continuous learning and adaptation. We encounter different blend shapes and rigs, and we constantly explore new software, acquire new skills, and discover innovative ways to handle 3D. By focusing on custom orders and tailor-made 3D models, we are consistently challenged, which contributes to our growth and development as professionals in the field.

Let’s Work Together

Are you in need of high-quality digital doubles for your next project? Look no further! Eisko is here to collaborate with you and bring your visions to life. Our team, with their extensive knowledge and passion for rigging, can help transform your 3D models into animated, lifelike characters. With our cutting-edge rigging techniques and attention to detail, we ensure that your digital doubles possess fluid movement, realistic expressions, and the ability to seamlessly interact with their virtual environment. Whether you’re working on a film, video game, virtual reality experience, or any other creative endeavor, our team is equipped to handle the rigging needs of diverse projects. Reach out to us today and let’s embark on an exciting journey together!

    First name

    Last name

    Company

    Email

    Your Message

    Deepfake of Jean Dujardin and Sean Connery in James Bond Dr No thanks to Eisko AI Face Replacement

    How we made a face swap of James Bond with Eisko AI Face Replacement?

    by Non classé


    Have you ever wondered what it would be like if Sean Connery was replaced by Jean Dujardin in the classic James Bond film Dr. No? Thanks to Eisko’s AI Face Replacement technology, we were able to make it a reality.

    We’ll take you behind the scenes of this project and show you how we were able to create a seamless face replacement using our proprietary deep learning tools.

     

    What is Eisko AI Face Replacement?

    Eisko A.I. Face Replacement is a proprietary deep learning technology developed by Eisko that goes beyond traditional deepfakes. It allows for a groundbreaking resolution of 1024×1024 and uses an enhanced model training method to create state-of-the-art face swapping for the film and video game industry.

    Our machine learning team has developed a protocol for face capture in our scanning system to preserve the exact expressiveness and performance of the person being reproduced.

    With Eisko’s AI Face Replacement, it’s possible to create high-quality animated faces or final composited videos that are ready to use.

     

    Creating the Sean Connery and Jean Dujardin Deepfake

    For this project, our team used Eisko’s AI Face Replacement technology to replace Sean Connery’s face with that of Jean Dujardin in the classic James Bond film Dr. No. We started by creating a machine learning training dataset based on existing photos of Sean Connery and Jean Dujardin. This dataset allowed our technology to learn the facial features and expressions of each actor, which was crucial for creating a convincing deepfake.

    Once we had the dataset, we used Eisko’s proprietary deep learning tools to create the face replacement. Our technology accurately captures the expressiveness of the person being emulated and is affected by all light, action, and occlusion conditions for seamless compositing. To enhance the realism of the deepfake, we added three layers of compositing: grain uniformity, color balance, and balance of highlights and shadows.

    The end result was a high-quality face swap of Jean Dujardin as James Bond that was almost indistinguishable from the original footage. Thanks to Eisko’s A.I. Face Replacement technology, we were able to create a seamless face replacement that captured the exact expressiveness and performance of Jean Dujardin.

     

    The Future of Face Replacement

    Eisko’s A.I. Face Replacement technology is not just limited to face swaps in films and video games. It can also be used to create digital doubles for stunts or to revive deceased persons. With the ability to create high-quality animated faces or final composited videos that are ready to use, Eisko’s A.I. Face Replacement technology is a game-changer for the entertainment industry.

     

    Let’s Work Together

    Eisko’s A.I. Face Replacement technology is a groundbreaking tool that pushes the limits of traditional deepfakes. With a resolution of 1024×1024 and an enhanced model training method, it allows for high-quality face replacements that accurately capture the expressiveness and performance of the person being emulated.

    The Sean Connery/Jean Dujardin deepfake is just the beginning of what’s possible with Eisko’s A.I. Face Replacement technology and we can’t wait to collaborate on your next project.

     

      First name

      Last name

      Company

      Email

      Your Message

      A face is shown in front of a digital background.

      How face swapping deepfake is changing the film industry forever

      by Non classé

      The world of movies and TV shows has always been fascinated by the idea of swapping faces. Whether it’s bringing back a deceased actor to life, creating a digital double for stunts, or de-aging an actor to make them look younger, the possibilities are endless.

       

      For years, VFX companies have been using traditional techniques like rotoscoping and 3D modeling to achieve these effects, but the emergence of artificial intelligence and deepfake technologies have changed everything. Face swapping deepfakes are revolutionizing the movie industry with their ability to create realistic and seamless face swaps, and do it all in a fraction of the time it used to take with older VFX techniques.

       

      But with new technologies always come with a whole host of ethical and privacy concerns that we must navigate as a society.

       

      Rotoscoping: the VFX face swapping traditional technique

      Before the advent of deepfakes, VFX (Visual Effects) companies employed various techniques to swap faces in movies and TV shows.

       

      One of the most common methods was to use a technique called “rotoscoping.”

      Rotoscoping involves manually tracing the subject’s face frame-by-frame in a video, using specialized software such as Adobe After Effects or Maya. Once the face is traced, the VFX artist can apply a new image or face onto the traced area using various compositing techniques, such as keying or tracking.

       

      Another method used by VFX companies was to employ 3D modeling and animation software to create a 3D model of the subject’s face. The VFX artist would then animate the 3D model to match the movements and expressions of the subject in the original footage, and then render the final result with the new face.

       

      Both of these techniques required a lot of time and skill to achieve a convincing result, and were typically used only for major film or TV productions where the budget and timeline allowed for such extensive post-production work.

       

      Deepfake: the machine learning face swapping to rule them all

      Face swapping deepfakes use a type of machine learning algorithm called a generative adversarial network (GAN) to swap the face of one person onto another person’s body in a video or image.

       

      Here’s how it works:

      • Training Data: The GAN is trained on a dataset of images and videos of both the person whose face will be replaced (the “source”) and the person whose body will be used (the “target”).
      • Face Detection: The GAN uses facial recognition algorithms to detect the position and features of the source face in the video or image.
      • Face Embeddings: The GAN then generates a “face embedding” for the source face, which is a mathematical representation of the unique features of the face. This is done using a type of neural network called an encoder.
      • Body Swapping: The GAN then swaps the source face onto the target body using another neural network called a decoder. This creates a new image or video that shows the target body with the source face.
      • Post-Processing: At EISKO, this step is fundamental and is realized by our 3D artist experts. This step includes color correction and smoothing for example.

      One of the biggest advantages of deepfakes compared to traditional techniques is the speed and efficiency with which they can be created. Deepfake algorithms can generate realistic-looking videos in a matter of days or hours depending on the target resolution, whereas traditional VFX techniques can take weeks to complete.

       

      Another advantage of deepfakes is the level of realism they can achieve. Deepfake algorithms use machine learning to analyze and replicate the facial features, expressions and movements of the original subject, resulting in a more accurate and seamless face swap. In contrast, traditional VFX techniques can sometimes result in a less convincing or “uncanny valley” effect, where the swapped face looks slightly off or unnatural.

       

      What about ethics and privacy ?

      Overall, the proliferation of deepfakes presents a significant challenge for society, as it requires us to rethink our approach to privacy, trust, and truth in the digital age. It also highlights the importance of responsible and ethical use of technology, as well as the need for education and awareness about the risks and implications of deepfakes.

       

      This question has been at the core of EISKO’s vision for over the past 10 years: the protection of digital identity. All those years, EISKO has developed its strategy and is now able to provide models that respect the privacy and security of the digital identity.

       

      Eisko’s AI Face Replacement Technology

      At EISKO, our face swapping deepfakes cover a large span of applications. Our deepfake can be used to create digital doubles of actors or performers. This can be useful for creating realistic stunts or action sequences without risking the safety of the actors.

       

      In addition tour face swapping algorithms can be used to bring deceased actors or famous people back to life for a movie or television show. For example, in the film “Rogue One: A Star Wars Story,” the character Grand Moff Tarkin was brought back to life using a combination of motion capture and face swapping techniques.

       

      Deepfake can also be used to digitally manipulate the appearance of actors or performers to make them appear younger, what’s called de-aging. The Marvel Cinematic Universe has used de-aging technology in a number of its movies, including “Captain Marvel” and “Ant-Man and The Wasp.” This technology was used to make actors Samuel L. Jackson and Michael Douglas appear younger in flashback scenes

       

      Those are some of the applications we have been working on. But what makes us stand out from the crowd is our proprietary state-of-the-art deepfake algorithm. This technology can be used for megapixel face swapping deepfake and is unique to EISKO.

       

      Contact us

        First name

        Last name

        Company

        Email

        Your Message

        Conversation with Eisko 3D virtual assistant

        Why 3D Virtual Assistant is the Future of Corporate Innovation?

        by Non classé

        As the world becomes more digital, companies are constantly looking for innovative ways to engage with their customers and streamline their operations. In recent years, the rise of artificial intelligence has led to the development of virtual assistants, which can help businesses automate tasks and improve the customer experience.

        However, the latest trend in this field is the emergence of 3D virtual assistants, which offer a more immersive and engaging experience than their text-based counterparts. In this article, we’ll explore why a 3D virtual assistant could be the next big thing in corporate innovation and how it can benefit businesses of all sizes.

         

        What is a 3D Virtual Assistant?

        A 3D virtual assistant is a CGI character that uses artificial intelligence to interact with users in a 3D space. Unlike traditional text-based chatbots, an ai-powered virtual assistant can simulate human-like movements and facial expressions, making them more engaging and realistic. They can also be customized to match a company’s brand, creating a more personalized experience for customers. Before, companies were using text-based chatbots, while now they can use their brand ambassadors a way to engage with their fans. Indeed, 3D virtual assistants can be used for a variety of tasks, such as customer service, sales, and marketing.

         

        Why are 3D Chatbots the Next Innovation for Companies

         

        Improved Customer Engagement

        According to a survey conducted by Salesforce, 64% of customers expect personalized engagement from companies. 3D virtual assistants can provide this level of personalization by simulating human-like interactions and facial expressions. This can lead to increased customer satisfaction and loyalty, as customers feel more connected to the brand.

         

        Increased Efficiency

        3D virtual assistants can automate tasks such as customer support, freeing up employees to focus on higher-level tasks. This can increase efficiency and productivity, leading to cost savings for the business. In addition, 3D virtual assistants can be available 24/7, providing around-the-clock support to customers.

         

        Better Brand Image

        By using a 3D virtual assistant, a company can show that they are at the forefront of technological innovation. This can improve their brand image and make them more attractive to younger, tech-savvy consumers. In addition, a well-designed 3D virtual assistant can help a company stand out from their competitors and create a unique brand identity.

         

        Future-Proofing

        As the technology behind 3D virtual assistants continues to improve, they will become even more sophisticated and versatile. By investing in a 3D virtual assistant now, companies can future-proof their operations and stay ahead of the curve.

         

        Why Choose a 3D Virtual Assistant from Eisko?

        Eisko is a leading provider of 3D Digital Doubles and offer breathtaking 3d avatar chatbots for businesses of all sizes. Our digital humans are created using 3D scanning technology combined with 3D artists expertise and can be customized to match a company’s brand and tone of voice. Eisko’s 3D virtual assistants are designed to be engaging and lifelike, providing a unique customer experience that sets businesses apart from their competitors. With their extensive experience in the film, gaming and cosmetic industries, Eisko is well-equipped to create 3D virtual assistants that are both emotionally engaging and technically advanced.

        In conclusion, 3D virtual assistants are the next big thing in corporate innovation, offering a more immersive and engaging experience than traditional text-based chatbots. By investing in a 3D virtual assistant, companies can improve their customer engagement, increase efficiency, and future-proof their operations. For businesses looking to stay ahead of the curve, an ai virtual assistant from Eisko is the perfect solution.

         

        To go further

         

        Contact us

          First name

          Last name

          Company

          Email

          Your Message

          Eisko's head and body 3D scanning systems

          What is the best 3D scanning technology for Film Productions? (Photogrammetry vs Photometry)

          by EntertainmentNon classé
          As the world of VFX, cinema, video games and advertising continues to evolve with ever more impressive visuals, so too does the 3D technology used to create them. 3D scanning has become a key tool for creating realistic digital doubles of celebrities, either it’s 3d scan of body of 3D scan of face. As technology advances, so do the possibilities for 3D scanning. From photogrammetry to photometry and even hybrid systems, there are a number of options available when it comes to creating 3D scans and digital doubles of actors for AAA production.
           
          In this article we’ll take an in-depth look at the two most prominent technologies used today – Photogrammetry and Photometry scanning – as well as discuss which is best suited for different cases.
           

          Best for full body 3D scan: Photogrammetry

          Photogrammetry has been around since 19th century but only recently has become popular among 3D professionals due to its accuracy in capturing detail from photographs taken from multiple angles. It was first developed by French photographer Aimé Laussedat who proposed using two cameras set at 90 degrees apart on either side of an object’s surface which would then take pictures from those angles simultaneously (Laussedat & Chavigny): the first 3D scanning system.
           
          It works by taking photos with overlapping fields of view then using software algorithms that measure points on each image before reconstructing them into a 3D model that can be manipulated further in postproduction workflows like adding textures, blendshapes etc. 3D photogrammetric scanning systems have become increasingly popular among professional visual effects directors, like 3d face scanner or 3D full body scanner.
           
          These human 3d scans offer high resolution textures along with precise 3D models suitable for use in cinematic scenes where realism needs to be achieved without compromising efficiency. It’s also efficient for large objects, for example with full body 3D scan.
           

          More accurate 3D scan of face: Photometry

          Photometry is very appreciated as a 3D facial scanner because it uses light sources placed at different angles relative to an object being scanned rather than cameras alone like photogrammetry does; thus enabling more accurate measurements because shadows created by these lights help define depth better than just camera images alone would allow – especially if the surface being scanned contains curves or irregular shapes (elements often found on human faces).
           
          More technically, it estimates the surface normals of an object by capturing it under different light orientations. It involves taking multiple pictures of the same object from different angles, then using the light and shadows of each image to calculate the surface normals of the object in 3D space.
           
          Another advantage of photometric 3D scanning is that it can capture surface texture and color information, making the 3D models look more realistic. It allows to capture PBR Textures (Physically Based Rendering) that typically include a color map, a roughness map, a metallic map, a normal map, and an ambient occlusion map.
          These textures are used to control the visual properties of a material, such as how it reflects light and how rough or glossy it appears.

           

          Which Technology For Which Case?

          When deciding between either technique one should consider their project requirements first. Do you need 3D head scan, 3D face scan or 3D body scan? If you need something fast yet precise enough, or 3D full body scans, then go ahead with photogammetry whereas if you really need extremely accurate results of 3D scan of humans even under complex lighting scenarios then opt instead for a hybrid system incorporating both technologies together – though bear in mind they tend come at higher costs associated due their complexity level.
           

          Eisko’s 3D scanning systems

          Eisko has developed several 3D scanning systems to make the best Digital Doubles, either it’s 3D body scanner or 3D head scanner.
           
          Our full body 3D scanning system goes beyond standards by applying 120 cameras to a photogrammetric technology. It allows quick and precise 3D scans of actors, props, objects and accessories, and permits photo-realistic 3D models.
           
          We also have developed a proprietary technology for 3D scan of heads and 3D scan of faces : we have a geometric accuracy free of bias and PBR (physically based rendering) textures of physical materials. Today’s rendering engines use PBR technology, they are oriented by a physical simulation of light.
           
          In short, by if you need the best quality 3D scan in Paris or worldwide, let’s contact us!
           
           

          Go further:

          Let's make photorealistic 3D scans

          We'd love to hear about your project and find the best solutions for you.

          Contact us