Brock liked HomeMade Arduino Jet Engine.Troy Schrapel has added a new log for 6502/65C02 Emulator Library.professorwilliamsdantas liked 'pπ' - Projector + Raspberry Pi in a box.luis.charpentier liked Exploring the Microprofessor.Mike Mormando liked Open Autonomous Domestic Robots.blueage liked Electrokinetic sculpture.somethings_beeping on Know Audio: A Mess Of Cables.Gravis on Keep Track Of Your Google Calendar With This Custom Build.John on Keep Track Of Your Google Calendar With This Custom Build.Glen Akins on Rainbow DIP Switch Is The Coolest Way To Configure Your Project.max on Underwater Tanks Turn Energy Storage Upside-Down.The odd fade effect was present with mvtools if the threshold was not set well. With mvtools it simply works by counting the number of blocks that are not found on the next frame and if the number was above a threshold it just duplicated the frames instead (those blocks were linearly interpolated otherwise). The thing that mvtools did and the AI clearly isn’t is detecting scene change. It was also quite painful to get that working on debian, I used an ubuntu ppa that required me to recompile everything that came out of it and mpv (as it’s not compiled with vapoursynth support for debian). The main problem is that it ran on CPU only which limits the number of blocks, but there is a commercial video player that recreated the lib with opengl, don’t remember the name of it. It indeed had problems with depth of field blur but anime does not have this problem and the results were near perfect. Mvtools is not AI based or anything, it just cuts the video into blocks and tracks the motion of them between frames to generate the intermediate ones. I had that working for a while, but everything kept exploding, the results where pretty good and it was awesome for anime. That means you can interpolate to 60 FPS at play time. There is already a thing called mvtools which works with the vapoursynth python library that is integrated with mpv. Posted in Video Hacks Tagged animation, artificial intelligence, depth perception, frames per second, interpolation, video Post navigation
Adding extra frames for animation in cheetah 3d software#
The software is also free, runs on any computer with an appropriate graphics card, and is available on GitHub. Especially since the AI is aware of depth and preserves information about the distance of objects from the camera. While we’ve seen AI create art before, the improvement on traditionally produced video is a dramatic advancement. This allowed to increase his frame rate from 15 fps to 60 fps without having to actually create the additional frames. The program is able to interpolate between frames and create more frames to fill the spaces between the original. This is where the artificial intelligence comes in. As an animator, he notes that it’s orders of magnitude more difficult to get more frames than this with traditional methods, at least in his studio. His original animation of LEGO figures and sets was created at 15 frames per second. A new method can “fill in” frames to smooth out the appearance of the video, which was able to use this in one of his animated LEGO movies with some astonishing results. The uses of artificial intelligence and machine learning continue to expand, with one of the more recent implementations being video processing.
0 kommentar(er)
