Incredible Athena
Creating computer graphics for the film industry is a very complex process, requiring a lot of hardware resources, time and human resources. Intellectual, of course, as Comrade Lenin wrote. Today we will tell you about Bit Theory Inc. and its creator Allen Bolden, who, together with the team, does not just make beautiful pictures, but actually develops real artificial intelligence!
Creative artificial intelligence
The main trump card of BTI is the Athena software core, with which Bolden ... communicates. For example, he wants to see a scene with a green plane flying above the clouds, and writes in the special field “a green jet flies above the clouds”. In response, a ready-made visualization of the scene immediately appears, fully suitable for further refinement by computer graphics artists. But the coolest thing in all this is that Athena learns in the process of solving each problem, and then uses the accumulated "experience" in the following projects.
In many ways, Athena is similar to Watson, an artificial intelligence system developed by IBM. In 2011, she made a splash in the Jeopardy !, a television quiz that has its own game in Russia. Watson compared the questions of the quiz with a 15-terabyte knowledge base from various fields. As a result, the supercomputer defeated the two champions of the show: they received 200 and 300 thousand dollars each, and Watson hit the jackpot - a million.
The creator of Athena believes that Watson’s algorithm of actions can be compared to how the rational left brain works. Athena’s actions gravitate more towards another, creative hemisphere. The program understands what they write to it, but responds not with words, but with visualizations.
By the way, initially Bolden did not intend to create artificial intelligence at all. His career began at Marvel Comics, where he came as an intern and suddenly realized that he really liked programming. To study this case, he temporarily left work and entered the University of Berkeley. After graduating, Allen gained serious knowledge in the field of artificial intelligence and network infrastructure and returned back to Marvel. There, his colleagues were already waiting for him, who by this time had completely plunged into the film business: “Hey dude, you cut in computers, right?”
Bolden was asked to help solve a problem that arose during the implementation of one of the important projects. The deadline turned out to be tough - it was necessary to deal with everything in 5 days. This is where AI developments came in handy. “I just thought that my knowledge would do some calculations faster, but in the end, it turned out something much more,” says Allen.
So, Athena turns natural language into a quality workpiece for the future visual product. Bolden sees the main goal of his development in making the work of computer graphic artists more creative, and transfer the entire routine like code and settings for creating animations to Athena's virtual shoulders.
By the way, when Bolden writes something to the program that she cannot understand, Athena puts up a series of question marks in this place. Further, Allen has two options - to make a more detailed description or to give a link to the desired visual object, already created manually. After Athena completes her work, the artists take her results as the basis for work in Maya and 3ds MAX. While they bring the schedule to the ideal, Athena seems to be “observing” what the experts are doing, storing all the actions in its ever-growing database in order to use the “knowledge” in the future.
The action algorithm for the graphs is as follows: first, artists cut out fragments with actors, effects and other moving objects from each frame, then fill the frame with visualization of the environment and then completely recreate the entire scene in 3D.
Necessary performance
When Bolden created Athena, the system used a cluster of 70 computers for work, and at the same time any other auxiliary computers Allen managed to get. Today Athena is working with a cluster of 30 Lenovo ThinkStation D20: they are mainly equipped with two Intel quad-core processors.
Two years ago, Bolden ran a team of 45 computer graphics artists. Today, the company has 150 schedules in the United States plus external employees from Taiwan, Hong Kong and Seoul. In addition to Lenovo workstations that host the entire Athena knowledge base, the BTI team uses the ThinkStation D20, C20 and S20.
Bolden estimates that BTI will visualize about 10,000 frames per week. Considering that there are 24 frames in one second, the output is about 7 minutes of the finished video. Of course, the team needs a lot of memory to work with such "heavy" material. Currently, an array of hard drives with a total capacity of 17 TB is used in a RAID1 configuration. Of course, this is not about the entire BTI database, but about the operational storage on which all work is directly performed.
Bolden compared the speed of the different computers that he used. For example, a fragment from the movie "Transformers: The Dark Side of the Moon" with a length of 196 frames, the system with a six-core processor and 8 GB of RAM processed for 96 minutes. And Lenovo ThinkStation D20 with two quad-core Xeon and 12 GB of RAM coped with the same task in just 25 minutes.
In another test, Bolden required to visualize 21 objects covered in hair drawn by computer graphic artists in Autodesk Maya. There were more than 140,000 individual hairs! The Lenovo Think Station S20 dealt with each frame in about 5 minutes, while the other computers Bolden had at their disposal simply did not carry out such a task.
And BTI's leading specialist in converting 2D graphics to 3D says that before its main program (NUKE by The Foundry) constantly “crashed” when solving complex problems, almost a couple of times a day. After the Lenovo ThinkStation D20 appeared in the company, nothing of the sort happens at all.
BTI Plans
Allen Bolden, of course, continues to perfect Athena day after day. His goal is to constantly improve the efficiency of work processes, he wants to make the production of computer graphics faster and cheaper without loss of quality. But the system is still at an early stage of development, so BTI launched an 18-month R&D project. The creator of Athena believes that productivity will increase significantly if you run the software core on 40 Lenovo workstations at the same time. Therein lies the tangible commercial potential of using Athena in external projects, and not just inside BTI.
Creative artificial intelligence
The main trump card of BTI is the Athena software core, with which Bolden ... communicates. For example, he wants to see a scene with a green plane flying above the clouds, and writes in the special field “a green jet flies above the clouds”. In response, a ready-made visualization of the scene immediately appears, fully suitable for further refinement by computer graphics artists. But the coolest thing in all this is that Athena learns in the process of solving each problem, and then uses the accumulated "experience" in the following projects.
In many ways, Athena is similar to Watson, an artificial intelligence system developed by IBM. In 2011, she made a splash in the Jeopardy !, a television quiz that has its own game in Russia. Watson compared the questions of the quiz with a 15-terabyte knowledge base from various fields. As a result, the supercomputer defeated the two champions of the show: they received 200 and 300 thousand dollars each, and Watson hit the jackpot - a million.
The creator of Athena believes that Watson’s algorithm of actions can be compared to how the rational left brain works. Athena’s actions gravitate more towards another, creative hemisphere. The program understands what they write to it, but responds not with words, but with visualizations.
By the way, initially Bolden did not intend to create artificial intelligence at all. His career began at Marvel Comics, where he came as an intern and suddenly realized that he really liked programming. To study this case, he temporarily left work and entered the University of Berkeley. After graduating, Allen gained serious knowledge in the field of artificial intelligence and network infrastructure and returned back to Marvel. There, his colleagues were already waiting for him, who by this time had completely plunged into the film business: “Hey dude, you cut in computers, right?”
Bolden was asked to help solve a problem that arose during the implementation of one of the important projects. The deadline turned out to be tough - it was necessary to deal with everything in 5 days. This is where AI developments came in handy. “I just thought that my knowledge would do some calculations faster, but in the end, it turned out something much more,” says Allen.
So, Athena turns natural language into a quality workpiece for the future visual product. Bolden sees the main goal of his development in making the work of computer graphic artists more creative, and transfer the entire routine like code and settings for creating animations to Athena's virtual shoulders.
By the way, when Bolden writes something to the program that she cannot understand, Athena puts up a series of question marks in this place. Further, Allen has two options - to make a more detailed description or to give a link to the desired visual object, already created manually. After Athena completes her work, the artists take her results as the basis for work in Maya and 3ds MAX. While they bring the schedule to the ideal, Athena seems to be “observing” what the experts are doing, storing all the actions in its ever-growing database in order to use the “knowledge” in the future.
The action algorithm for the graphs is as follows: first, artists cut out fragments with actors, effects and other moving objects from each frame, then fill the frame with visualization of the environment and then completely recreate the entire scene in 3D.
Necessary performance
When Bolden created Athena, the system used a cluster of 70 computers for work, and at the same time any other auxiliary computers Allen managed to get. Today Athena is working with a cluster of 30 Lenovo ThinkStation D20: they are mainly equipped with two Intel quad-core processors.
Two years ago, Bolden ran a team of 45 computer graphics artists. Today, the company has 150 schedules in the United States plus external employees from Taiwan, Hong Kong and Seoul. In addition to Lenovo workstations that host the entire Athena knowledge base, the BTI team uses the ThinkStation D20, C20 and S20.
Bolden estimates that BTI will visualize about 10,000 frames per week. Considering that there are 24 frames in one second, the output is about 7 minutes of the finished video. Of course, the team needs a lot of memory to work with such "heavy" material. Currently, an array of hard drives with a total capacity of 17 TB is used in a RAID1 configuration. Of course, this is not about the entire BTI database, but about the operational storage on which all work is directly performed.
Bolden compared the speed of the different computers that he used. For example, a fragment from the movie "Transformers: The Dark Side of the Moon" with a length of 196 frames, the system with a six-core processor and 8 GB of RAM processed for 96 minutes. And Lenovo ThinkStation D20 with two quad-core Xeon and 12 GB of RAM coped with the same task in just 25 minutes.
In another test, Bolden required to visualize 21 objects covered in hair drawn by computer graphic artists in Autodesk Maya. There were more than 140,000 individual hairs! The Lenovo Think Station S20 dealt with each frame in about 5 minutes, while the other computers Bolden had at their disposal simply did not carry out such a task.
And BTI's leading specialist in converting 2D graphics to 3D says that before its main program (NUKE by The Foundry) constantly “crashed” when solving complex problems, almost a couple of times a day. After the Lenovo ThinkStation D20 appeared in the company, nothing of the sort happens at all.
BTI Plans
Allen Bolden, of course, continues to perfect Athena day after day. His goal is to constantly improve the efficiency of work processes, he wants to make the production of computer graphics faster and cheaper without loss of quality. But the system is still at an early stage of development, so BTI launched an 18-month R&D project. The creator of Athena believes that productivity will increase significantly if you run the software core on 40 Lenovo workstations at the same time. Therein lies the tangible commercial potential of using Athena in external projects, and not just inside BTI.