(PG2023/CGF) This is the official PyTorch implementation of PG2023/CGF paper: GA-Sketching: Shape Modeling from Multi-View Sketching with Geometry-Aligned Deep Implicit Functions
I find that in edit_widget.py, there are some functions about shadow, and I also check the paper ShadowDraw. My problem is, is the Data Generation step necessary? Is it for building a shadow dataset to guide the users? Can you provide thoes images or I have to build it myself?
Many thanks!
You can ignore related codes about shadow. Without it, it may be a little difficult to draw the correct sketch consistent with the viewpoint.
You can randomly select some samples from the dataset to generate the shadow, as I do. I generate the dataset via the scripts under tools/sketch_rendering/. Here I have provided same samples in sketch_transparent_20.zip.
You can use some fixed samples to generate the shadow.
I find that in edit_widget.py, there are some functions about shadow, and I also check the paper ShadowDraw. My problem is, is the Data Generation step necessary? Is it for building a shadow dataset to guide the users? Can you provide thoes images or I have to build it myself? Many thanks!