Look at the sofas that came up from the application of PU foam in the 60’s, it was almost as if the PU foam was asking to be modeled in this shape.
Look at the styles that came up from architects that were exploiting concrete to its limit: they came up with Brutalism.
Look at the peculiar style that emerged from blacksmiths in the 1800s. They had a limited number of operations to model metal rods, and that operations forged the style.

Look at the tools which are used now and you will have a spectrum of styles.

So, if there is a limited dialogue between the mesh based tools and CAD used to manufacture physical goods, you will have more expressions influenced by CAD.

Now we can manufacture potentially any shape with the available manufacturing technology, and a lot of shapes are still lofts and cut extrudes. This could be remembered as the golden age of CAD in Industrial design, producing many great products with this peculiar style guided by parametric functions.

---

---

Polygonal modeling is the most widespread and versatile 3D modeling technique. The expressive potential and usability of this technique should be a must have for industrial designers. But we are far from using its full potential.

Meshes can describe any 3D shape, with a level of precision that depends on the number of polygons. Game assets are optimized to save computing resources. Based on Subdivision surfaces, while working on a few polygons, they describe complex and polished surfaces.
In this conceptually simple way, artists can create complex and amazing shapes, in an easy way. So why aren’t we seeing it everywhere on the industrial design 3d modeling pipeline?

The standard in industrial design is modeling with Parametric surfaces, which I call NURBS. It’s the surface-generating “language” on which Rhinoceros 3D is based, ideal for modeling automotive-style, aerodynamic shapes.
The precision and control you get with parametric surfaces are much higher, but I think that large organisations continue to use the same software that their employees already master (it is a legacy system) and resist change.

The problem

The shapes that come up quite easily with subdivision surfaces require much more effort to be made with paramedic surfaces. It’s not a lack of imagination, will or ability from designers. It’s as if the program decides what you can and cannot do, while outside the industrial design world, professionals continue to produce great models and renders at a impressive rate, thanks to software like Zbrush, Maya, Blender, Max, with the tools and user interface which are 20 years head start.

While prominent design firms keep using cut extrudes and lofts, with good looking rounded edges, game design is experiencing the equivalent of the renaissance in terms of style and new ideas.

How is it possible that the complexity of the shapes in products is so basic? Is it just because everyone follows Dieter Rams teachings? Why everything seems copied from Apple products? I’m saying that it’s not just fashion, it’s lack of tools.

T-splines tried to bridge this gap by offering a plugin for Rhino, recently integrated in Autodesk Fusion360, while Creo Parametric offers freestyle, a great way to import and edit a lo-poly mesh into a parametric software.
Until now, these programs had a limited number of functions, and it seems hard to catch up with the mesh modeling interface.

---

I think industrial designers should integrate organic modeling features alongside the classic parametric tool. Not just to “explore” new shapes, as advertised by some software houses, even though that is a great step forward.

Subdivision surfaces and the advanced modeling interface you see in Zbrush and Blender should be merged seamlessly into the industrial design workflow, because the advantage to create gorgeous shapes is great, and most of all, it shouldn’t be painful.

Working for the toy industry in the last 4 years I sculpted meshes on Zbrush and imported the obj on my favorite parametric softwares. Could Rhino 7 solve the problem? It seems to deliver quite well, so far.