This was our final week of the semester. We gave our final presentation at EA on Wednesday (May 8, 2019). Here’s our final presentation: This was followed by a final play-through of our game by our faculty in Pittsburgh. To speed up the demo process, we asked our faculty to send us videos in advance.…
Read more
As we are one week away from our Finals Presentation, we are wrapping up our demo and working to polish our documentation for hand-off. PROGRAMMING We tried another approach for our ML pipeline. This approach uses Openpose + Motion Reconstruction. While this approach led to improvement in the capture of movement details, it does not…
Read more
PROGRAMMING AND ART This week, we focused on improving the quality of the animations which are recreated. The machine learning pipeline gives output as animation data (bvh) file, which is meant for a specific Blender skeleton. We realized that we were trying to solve a very difficult problem, by trying to re-target animation data in…
Read more
This week we focused on improving the recreation of animations, improving the animation quality and adding moments in the experience to enhance the cinematic quality. We met our client this week and showed our demo. We got positive feedback about our cinematic experience, and some suggestions to improve it. Here are the three main points…
Read more
DESIGN We tweaked our storytelling experience’s design to focus on the game’s core loop. With this in mind, we added context to the storytelling experience in a way that the resulting experience is a cinematic experience. The context of our experience is still a film boot-camp as discussed in the Week 10 blog post. However…
Read more
PROGRAMMING This week we created a demo which demonstrates our entire machine learning pipeline as well as user experience flow. Here’s how it works In the beginning, the user is given prompts to perform movements and record them as videos. The user must then upload the videos to a specific Google Drive location. We then…
Read more
PROGRAMMING As previously stated we are using a Google Cloud Virtual Machine to speed up the machine learning computations, which is required to achieve an acceptable video processing time. This means that the user videos need to be stored in a place where they can be accessed by the Google Cloud Virtual Machine. One of…
Read more
This week most of our team was at Game Developers Conference in San Francisco. However we arrived at a decision about which game we want to build for our final deliverable. We decided to move ahead with the storytelling idea. Here are some reasons for the same: The storytelling idea solves one of the main…
Read more
This week we we had our halves presentation. We spent most of our time preparing for halves and the rest of it building the prototype for our demo. We added UI to let players choose from a pool of animations to solve the puzzle. We also brought our cat character into the prototype. On the…
Read more
This week we made progress on getting the entire pipeline working from 2-D Videos to animation data, and furthermore bringing this animation data inside Unreal to create animations. We also finished implementing the core mechanics of our puzzle prototype. We recorded videos of people doing movements to test ideal conditions for recording videos. On the…
Read more
