Closed nicetryzz closed 3 months ago
Hi @nicetryzz
This is expected. As the numerical gradient step becomes smaller, more geometric details are generated due to coarse-to-fine control, which means larger curvature weight. If you want smoother surface, increasing the curvature weight would help at the cost of details. I hope this helps!
Thanks for your work! I test the meeting room in tank and temples datasets. The training curvature loss is strange. It increases a lot when reduces curvature weight. Should I increase the curvature weight?
curvature loss:![W B Chart 2023_12_18 13_18_55](https://github.com/NVlabs/neuralangelo/assets/70940473/cd998497-1243-4776-b616-2053a8e24452)
I test in 4 16G Tesla P100. Parameter as below: