We could implement a way to remove the motion blur using AI model: https://github.com/google-research/maxim

Then using the new AI-based optical flow, we can add the motion blur back after stabilization

For reference:

• https://github.com/bevyengine/bevy/pull/9924/files
• https://github.com/phiresky/opencl-motion-interpolation
• https://github.com/OpenCL/GEGL-OpenCL/blob/master/opencl/motion-blur-linear.cl