Our next topic is Garment design. The work we introduce here is sensitive couture for interactive garment editing and modeling. So, the problem we want to address here, is the design of a new novel original garment. And again, this is very difficult for inexperienced people. So, you have 2D cross pattern, and then you have three dimensional garment on the body. and it's, what you want is three dimensional shape. But what you have to control is two dimensional shape. And it's very difficult to imagine what 2D pattern you have to get to get the desired 3D shape. So, that's a problem we what to address. And our approach is the same as the previous ones. So we learn continuous concurrent simulation behind the scene. So user continuously edits the shape- 2D pattern with mouth operation and the system continuously applies physical draping clothes simulation. So user can directly edit 2D shape while watching the clothing in the 3D configuration. So that's the idea. So the same as before, on the left side, you see 2D clothes patterns the user is editing. And on the ride si- on the right side you see clothing, putting onto the 3D body. And here the simulation is much more accurate than the one I showed for the stuffed animal design. So you can actually predict details, wrinkles and so on. So you can interactively edit the 2D pattern. And the system interactively updates the clothing, draping simulation results. So you can actually see small wrinkles here. And then you can edit the shape. So as to reduce wrinkles if necessary. So traditionally, if you want to do this, you have to actually physically cut paper or a cloth material, stitch together and put on the mannequin, physical mannequin. And run draping and see the result and then go back to the 2D pattern and cut, stitch again. So it can be very, very long, long time, it's very slow. And also computer-based simulation is also available. It's similar. You have to move to simulation engine, run simulation and then go back to the design. That's a problem. And also, technically, it's very, challenge to run physical simulations so rapidly. Of course there are real time rapid clothes simulation existing already. But they, these physical simulation is for animation. So they assume fixed clothes pattern. So clothes geometry doesn't change. And then system learns lots of precomputation for efficient computation real-time. And then just draping run animation. To run simulation to create animation. However, here, the system, the user continuously change the rest shape. Which is, violates the assumption of standard animation, animation simulation engine so that's the challenge we have to address. So if you do not like a wrinkle here, then you can just interactively add dart here. And then, you can immediately see how the resulting clothing looks more natural. Okay, so this is one example and here's more examples. So, yeah, so design of t-shirt or garment for human character is not actually so difficult. There are many standard ways to design a garment. However, if you want to design a pajama for armadillo like here, it's a very difficult problem. No one knows how to design a character shirt. And especially if you wanted to buy a physically valid garment, it's very difficult, and this kind of design tool can be very, very useful. So previously in computer graphics, garment of this character is a very quash mesh, there's no physics, just a polygonal mesh. But recently, game engines are very fast, more efficient. So we use, people starting to use physical simulation for these garments. Now then, it's necessary to design physically valid garments. So that's the reason why you need these kind of tools. So here is a comparison with the real one. The left side is a computer graphics view in your simulation, and the right hand side is the physical construction. So we 3D printed this kind of character and also we physically stitched together this garment. And as you see, of course, it is not 100 millimeter size exact match. However, you see the general pattern like sleeve folds here and then you see sleeve folds here. So I think this is enough for our initial design. And we also design real size garments using system. So this is just, just screen snapshot. So user interactively edits the shape And then you see continuously see the 3D result. And then we print it into a larger format, real size print. And then you put pattern into a cloth and then you stitch together and then you get a wearable results. Okay. So let me briefly describe the algorithm. So, again, the oh, complete implementation is beyond the scope of this short video. But I can briefly describe the basic idea behind it. How to make it faster. So this is a fundamental equation. Mathematical representation of the problem we tried to solve here. So we have 2D input pattern. This is the input from the user. So user specify 2D clothes pattern. And then what we, want to compute is 3D cloth shape. So, yeah. So input these XY coordinate positions of input clothes, and output is XYZ position of individual vertices so 3D clothes shape, this is the output you want to get. And then we cover function, that represents the relationship between 2D cloth pattern input and cloth- 3D cloth shape output. And this function returns 0, if it is satisfies the physically valid natural shape. And this function is called resi- residual. So if the configuration 3D cloth shape is not in the desired, appropriate physically valid shape. This residual becomes bigger, larger. And then we, we gradually, this residual are smaller. They get more physically realistic results. So that's the problem we try to solve. And visually, the situation looks like this. So you have a space of valid designs. And on this view, on this axis, you have many different two dimensional cloth patterns. So user specifies starts from this pattern and then moves to another pattern, as user edit. And for each shape, you have a single iso surface, or specific region, where R becomes 0. So here, it's represented as a single line, single curved line. So, for the given 2D clothes pattern, we take a look at the region where the R equals 0. And then look at the 3D shape, and then you will get the proper 3D output. So this is a, very very simplified view of what's going on internally. The problem is that, problem’s here. So R, the residual is very highly non-linear and very, very slow to compute. So, yes, so R 0 is very curved and very complicated. When you change the pattern, you have to recompute R, which takes too much time. So we, what we use is a kind of a stanadard. But we use a linear appro- approximation around the current state. So visually, it looks like this. So, this a current design and then you compute the linear appro- approximation of this residual function. And this method is called, called sensitivity analysis in structural analysis. And then after computing linear approximation it's kind of easy, to predict the, compute from 2D input shape to 3D shape. Just by solving our linear system. Which is faster. Of course, this is an approximation near this design. So, if you go farther away, then it's, it becomes too different. So in your system. So single linear approximation is not enough Users who're dragging far away from the linear state. The difference from the real physically realistic result gets bigger. So in that case, we compute another approximation here like this way. And then, so we cache multiple linear approximations occasionally and then blend them. So, in this case, if you have two examples and if you blend these two, you get a very, very close approximation. And this is still very fast to compute. So that's what we do in internally. So caching happens occasionally. So, the user, the system continuously monitors. Users dragging operation. And then when the users dragging is getting far away, you create another cache. Now you have two cache, and if you move far away from these two caches, the system will generate another. So in this way, the system incrementally add more and more caches. So this is a summary. So we presented garment design with concurrent physical simulation. So user interactively edits a 2D pattern. And then system presents the 3D draping results. And then we apply, sensitivity analysis which is linear approximation. And those multiple caches for providing rapid feedback without running simulation from scratch each time. So, to learn more the original paper was published as Sensitive Couture for Interactive Garment Editing and Modeling. And garment design is also a hot, popular topic in graphics community. And one example is Virtual Garments, A Fully Geometric Approach for Clothing Design. So, in this project, they did not use any physical simulation. Purely geometric approach, but the, but they can rapidly generate reasonable shapes this way. Thank you.
