If you have a supported GPU install pytorch with GPU support.
However, it does speed up the process significantly. The neural network that does the heavy lifting is written for PyTorch.Ī Nvidia GPU is recommended but not necessarily required. Open automask.py in your favorite text editor and replace PYTHON_PATH with the path to you python site-packages if needed and PROJECT_DIR with the path to the directory you downloaded this repository to.
The Blender python or if python is already installed on the system and the python version is compatible with the Blender python version you can also install the dependencies on your system. You can either install the dependencies to To use this Add-on, several 3rd party libraries are required (see requirements.txt).
zip file and extract it or clone it to your computer.
Threshold is the amount of pixels that can go in another direction than the rest of a given segment.ĭownload the repository as. 2 will produce more controll points but a closer match in the mask, but the S-Curves can also handle 3 different directions. Directions is the amount of directions (of 8 possible) one mask segment can cover. Bear in mind that the network output is by no means a perfect mask. The lower this value is the closer the final mask will be to the network output. Length is the roughly the maximum amount of pixels a mask segment can trace. If you are using the single step masking as a starting point for your mask you can also Parameters The masks for every frame will be saved in a separate and new Mask Layer. Here is an example for the usage of AutoMask.įirst select a bounding box of the object. This repository contains a Blender 2.8x Add-on that can mask an object in the Movie Clip Editor with the help of Machine Learning.ĪutoMask is the communication between Blender and SiamMask. AutoMask - a Blender Add-on for automatic rotoscoping
0 kommentar(er)
