Sohre, Nicholas (University of Minnesota) | Adeagbo, Moses (University of Minnesota) | Helwig, Nathaniel (University of Minnesota) | Lyford-Pike, Sofia (University of Minnesota) | Guy, Stephen J. (University of Minnesota)
Animating digital characters has an important role in computer assisted experiences, from video games to movies to interactive robotics. A critical challenge in the field is to generate animations which accurately reflect the state of the animated characters, without looking repetitive or unnatural. In this work, we investigate the problem of procedurally generating a diverse variety of facial animations that express a given semantic quality (e.g., very happy). To that end, we introduce a new learning heuristic called Precision Variety Learning (PVL) which actively identifies and exploits the fundamental trade-off between precision (how accurate positive labels are) and variety (how diverse the set of positive labels is). We both identify conditions where important theoretical properties can be guaranteed, and show good empirical performance in variety of conditions. Lastly, we apply our PVL heuristic to our motivating problem of generating smile animations, and perform several user studies to validate the ability of our method to produce a perceptually diverse variety of smiles for different target intensities.
Automatically generating animation from natural language text finds application in a number of areas e.g. movie script writing, instructional videos, and public safety. However, translating natural language text into animation is a challenging task. Existing text-to-animation systems can handle only very simple sentences, which limits their applications. In this paper, we develop a text-to-animation system which is capable of handling complex sentences. We achieve this by introducing a text simplification step into the process. Building on an existing animation generation system for screenwriting, we create a robust NLP pipeline to extract information from screenplays and map them to the system's knowledge base. We develop a set of linguistic transformation rules that simplify complex sentences. Information extracted from the simplified sentences is used to generate a rough storyboard and video depicting the text. Our sentence simplification module outperforms existing systems in terms of BLEU and SARI metrics.We further evaluated our system via a user study: 68 % participants believe that our system generates reasonable animation from input screenplays.
This essay discusses whether computers, using Artificial Intelligence (AI), could create art. First, the history of technologies that automated aspects of art is surveyed, including photography and animation. In each case, there were initial fears and denial of the technology, followed by a blossoming of new creative and professional opportunities for artists. The current hype and reality of Artificial Intelligence (AI) tools for art making is then discussed, together with predictions about how AI tools will be used. It is then speculated about whether it could ever happen that AI systems could be credited with authorship of artwork. It is theorized that art is something created by social agents, and so computers cannot be credited with authorship of art in our current understanding. A few ways that this could change are also hypothesized.
With the aim of creating virtual cloth deformations more similar to real world clothing, we propose a new computational framework that recasts three dimensional cloth deformation as an RGB image in a two dimensional pattern space. Then a three dimensional animation of cloth is equivalent to a sequence of two dimensional RGB images, which in turn are driven/choreographed via animation parameters such as joint angles. This allows us to leverage popular CNNs to learn cloth deformations in image space. The two dimensional cloth pixels are extended into the real world via standard body skinning techniques, after which the RGB values are interpreted as texture offsets and displacement maps. Notably, we illustrate that our approach does not require accurate unclothed body shapes or robust skinning techniques. Additionally, we discuss how standard image based techniques such as image partitioning for higher resolution, GANs for merging partitioned image regions back together, etc., can readily be incorporated into our framework.
Technology, says Nalbandian, is one of the three pillars that drives Animal Logic – the other two being the group's strong creative department, and its ability to make commercially viable products – and now the technology is driving Animal Logic into a whole new world: artificial intelligence and machine learning. The artificial-intelligence technology, made popular by applications such as Google's Assistant and Amazon's Alexa voice assistants, is already being adopted by the global animation and visual-effects industries to cut out some of the processor-intensive work that computers have to do, and, says Nalbandian, it's going to be adopted at Animal Logic to cut out some of the labour-intensive work that the company's humans have to do, too. In 2018 Animal Logic hired its first chief technology officer, Darin Grant, an industry veteran who was previously in charge of production technology at Steven Spielberg's legendary DreamWorks Animation, and who later went on to work at Google. Speaking from his base in Los Angeles (Animal Logic now has offices in Los Angeles and Toronto, as well as its headquarters at Fox Studios in Sydney), Grant points out that there are computer-related tasks in the animation and visual effects industry that have been moved over to machine learning, simply because the technology is more efficient. Rather than animate characters like i Peter Rabbit /i's Flopsy, Mopsy, Benjamin and Cottontail themselves, Animal Logic's artists may one day be able to teach an AI machine how to do it, leaving the artists free for even more ambitious work.