diffmat
diffmat copied to clipboard
PyTorch-based differentiable material graph library for procedural material capture
just run some test target image is  and run the following command: ``` python .\test_optimizer.py .\sbs\match_v1\bricks.sbs -e -im bricks.jpg python .\test_hybrid_optimizer.py .\sbs\match_v1\bricks.sbs -e -im bricks.jpg -m combine -ip .\result\bricks\optim_bricks\checkpoints\optimized.pth...
This is a valuable work. But I still have a question, if a certain material (such as **metal or wood or fabric**) is optimized, will the optimization result still maintain...