Mo goes over how to generate a depth map from a single image and use it in Houdini’s Karma XPU to render a relief like geometry.
Download Project Files: https://www.entagma.com/downloads/AI_Houdini_depthmap.zip
Mo goes over how to generate a depth map from a single image and use it in Houdini’s Karma XPU to render a relief like geometry.
Download Project Files: https://www.entagma.com/downloads/AI_Houdini_depthmap.zip
The generative AI is great! I am excited at the prevalence of 2.5D content generation but feel that things such as Human Motion Generation will be the biggest game changer.
It would be wonderful if you could have a look at the concept of “Differentiable Houdini”, where node networks are optimized using differentiable rendering. Maybe using different types of Diff nodes for loss functions. Two article titles that I find interesting are:
Node Graph Optimization Using Differentiable Proxies
Automatic Differentiable Procedural Modeling