Back
Similar todos
fail w/medium dataset from 360 video (~6,000 images) like small, but full requires too much memory, next strategy is render each input separately 
#mused
test pipeline choosing least blurry image out of every 120 frames for smaller datasets #mused
testing with 3d model generator
test new method eq 2 perspectives for processing 360 video frames #mused
render out two videos from neural networks on tiny datasets to test new method of capture & pipeline #mused
Get test shots for overhead video 
#sp
training on full dataset is taking too long so export just the Kings Chamber 360s for testing #mused
Generate more test images of my Fallout adaptation with realistic model 
#melies
test video recording with small demo
test conversions of 360 images to rectilinear for making splats, about 80 v&h fov gives best result so far #mused
investigate persistant image rec tracking 
#witness