Collaborating Authors


[Project] blendtorch: seamless PyTorch - Blender integration


Training with artificial images is becoming increasingly important to address the lack of real data sets in various niche areas. Yet, many today's approaches write 2D/3D simulations from scratch. To improve this situation and make better use of existing pipelines, we've been working towards an integration between Blender, an open-source real-time physics enabled animation software, and PyTorch. Today we announce blendtorch, an open-source Python library that seamlessly integrates distributed Blender renderings into PyTorch data pipelines at 60FPS (640x480 RGBA). Batch visualization from 4 Blender instances running a physics enabled falling cubes scene.

Space Render 1.0: Artificial Intelligence in 3D Animation


Space Render 1.0: Artificial Intelligence in 3D Animation Create wow-inspiring 3D Animation and VFX Video super-fast using Cloud-Based Artificial Intelligence (AI) Tools Typically traditional and normal animation learning focusses on learning complex CGI software which are prone to be difficult for newbies to master very quickly – unless the learners are technically strong. Of course, these kind of software work through deploying traditional frame-by-frame animation methods that take a tedious amount of time to complete a short animated film of 5 minutes duration. Bring in the Artificial Intelligence (AI) tools into this and this will drastically change the scenario – for sure. This course is a testament of the same. This mind-blowing course titled "Space Render 1.0: Artificial Intelligence in 3D Animation" created by Digital Marketing Legend "Srinidhi Ranganathan" and Mastermind "Saranya Srinidhi will teach you cloud based tools to achieve the same extraordinary output that is stunning enough to wow your crowd in a matter of HOURS.

Local Motion Phases Technique Boosts Basketball Animation Richness and Realism


Researchers from the University of Edinburgh School of Informatics and video game company Electronic Arts have proposed a novel framework that learns fast and dynamic character interactions. Trained on an unstructured basketball motion capture database, the model can animate multiple contacts between a player and the ball and other players and the environment. The team's modular and stable framework for data-driven character animation includes data processing, network training and runtime control; and was developed using Unity, Tensor flow, and PyTorch. The approach can perform complex and realistic animations of bipeds or quadrupeds engaged in sports and beyond. Enabling characters to perform a wide variety of dynamic fast-paced and quickly changing movements is a key challenge in character animation.

When working from home is much more than emailing

BBC News

Ere Santos remembers that he once had to animate a fight between his character, the sidekick, and the hero of the film. Luckily, the hero's animator sat next to Mr Santos. Much like their creations, the two colleagues went to battle on how the interaction should work. Instead of drawing, these feature film animators create computer simulations based on physics. Mr Santos likens it to making a puppet that the computer will bring to life.

6 Best Pixel Art Tutorial, Course and Certification 2020 JA Directives


Are you looking for the Best Pixel Art Tutorial? If you're a pixel artist who wants to create 8-bit animations or a game designer who wants to build tilesets for your new RPG video game, this top-rated course to help you achieve your goals. These online courses include both paid and free resources to assist you to learn Pixel Art. These tutorials are suitable for anyone from beginners, intermediate learners, and experts. In this Pixel Art Tutorial, Become an exquisite pixel artist and animator.

Learn how to design your own video game using Unreal Engine


TL;DR: Create your own fun with an online course called The Absolute Beginner's Guide to Learning Unreal Engine for Game Design and Animation for $40, a 96% savings as of June 8. Way back in 1998, a game engine called the Unreal Engine was developed and showcased in the first-person shooter game Unreal. More than two decades later, it's now used in a variety of other game genres, like platformers (think Super Mario Bros.), fighting games (think Mortal Kombat), MMORPGs (think World of Warcraft), and other RPGs (like The Legend of Zelda). Heck, it's even become a leading resource in the creation of animations, television shows, and illustrations. For all you curious gamers out there, you can learn to use this multi-purpose engine for yourself.

Four SCS Faculty Members Named University Professors

CMU School of Computer Science

Jessica Hodgins is a professor of computer science and robotics in the School of Computer Science and also directs the Facebook Artificial Intelligence Research laboratory in Pittsburgh. Her research focuses on computer graphics, animation and robotics with an emphasis on generating and analyzing human motion. She is the former vice president for research at Disney Research. Hodkins received her Ph.D. in computer science at CMU in 1989 and served as an associate professor and assistant dean in the College of Computing at the Georgia Institute of Technology before joining the CMU faculty in 2000. She served as associate director of faculty in the Robotics Institute from 2005 to 2015.

Computers Do Not Make Art, People Do

Communications of the ACM

We live in an age of amazing new visual art created with artificial intelligence (AI) technology. The recent wave began with neural stylization apps and the trippy, evocative DeepDream. Many fine artists now work with neural network algorithms, creating high-profile works appearing in major venues.1 Together with these new developments comes the hype: technologists who claim that their algorithms are artists and journalists who suggest that computers are creating art on their very own. This column explains why today's technologies do not create art; they are tools for artists. This is not a fringe viewpoint; it reflects mainstream understanding of both art and computer science.

The Impact of Python: How It Could Rule the AI World? - insideBIGDATA


Hold your head up high! The rise of artificial intelligence (AI) and machine learning (ML) are poised to bring a new era of civilization and not destroy them. Yet, there's fear that technology will displace the current workers or tasks, and that's partly true. As predicted by researches, the speed at which AI is replacing jobs is bound to skyrocket, impacting the jobs of several workers such as factory workers, accountants, radiologists, paralegal, and truckers. Shuffling and transformation of jobs around the workforce are being witnessed, thanks to the technological epoch.

Microsoft's AI generates 3D objects from 2D images


The AI research labs at Facebook, Nvidia, and startups like have at various points tried their hand at the challenge of 2D-object-to-3D-shape conversion. But in a new preprint paper, a team hailing from Microsoft Research detail a framework that they claim is the first "scalable" training technique for 3D models from 2D data. They say it can consistently learn to generate better shapes than existing models when trained with exclusively 2D images, which could be a boon for video game developers, ecommerce businesses, and animation studios that lack the means or expertise to create 3D shapes from scratch. In contrast to previous work, the researchers sought to take advantage of fully featured industrial renderers -- i.e., software that produces images from display data. To that end, they train a generative model for 3D shapes such that rendering the shapes generates images matching the distribution of a 2D data set.