11–20 of 105 posts
Pretty cool concept! I feel like it would have made more sense to get multiple samples of each frame, and let all the users upvote/downvote frame versions to arrive at the best ones.
Poor execution, but great idea. Give users random frames. Obtain multiple drawings for each frame. average and reject frames that are too different from the average. voila!
If they were fully shaded frames it would work, but hairlines I have no idea.
Also I observed that some frames left a dark background white, and others filled in a dark background as black. So you'd have to set up a lot of drawing "rules" to ensure it was even conceptually meaningful to generate an average in the first place.
Poor execution, but great idea. Give users random frames. Obtain multiple drawings for each frame. average and reject frames that are too different from the average. voila!
I can't even begin to guess how you would numerically average or compare hairline drawings. If they were fully shaded frames it would work, but hairlines I have no idea. Also I observed that some frames left a dark background white, and others filled in a dark background as black. So you'd have to set up a lot of drawing "rules" to ensure it was even conceptually meaningful to generate an average in the first place.
What are the copyright implications of this work? Is it legal to distribute the stitched together frames without audio? Do you think this project is going to get DMCAd off the internet?