| dc.description.abstract | A hallmark of early stage design is a number of quick‐and‐dirty sketches capturing design inspirations, model variations and alternate viewpoints of a visual concept. We present SketchSoup, a workflow that allows designers to explore the design space induced by such sketches. We take an unstructured collection of drawings as input, along with a small number of user‐provided correspondences as input. We register them using a multi‐image matching algorithm, and present them as a 2D interpolation space. By morphing sketches in this space, our approach produces plausible visualizations of shape and viewpoint variations despite the presence of sketch distortions that would prevent standard camera calibration and 3D reconstruction. In addition, our interpolated sketches can serve as inspiration for further drawings, which feed back into the design space as additional image inputs. SketchSoup thus fills a significant gap in the early ideation stage of conceptual design by allowing designers to make better informed choices before proceeding to more expensive 3D modelling and prototyping. From a technical standpoint, we describe an end‐to‐end system that judiciously combines and adapts various image processing techniques to the drawing domain—where the images are dominated not by colour, shading and texture, but by sketchy stroke contours.SketchSoup takes an unstructured set of sketches as input, along with a small number of correspondences (shown as red dots) (a), registers the sketches using an iterative match‐warp algorithm harnessing matching consistency across images (b, top) and embeds the sketches into a 2D interpolation space based on their shape differences (b, bottom). Users can explore the interpolation space to generate novel sketches, which are generated by warping existing sketches into alignment(c, top), followed by spatially non‐uniform blending (c, bottom). These interpolated sketches can serve as underlay to inspire new concepts (d), which can in turn be integrated into the interpolation space to iteratively generate more designs (e). (Some sketches courtesy Mike Serafin.)A hallmark of early stage design is a number of quick‐and‐dirty sketches capturing design inspirations, model variations and alternate viewpoints of a visual concept. We present SketchSoup, a workflow that allows designers to explore the design space induced by such sketches. We take an unstructured collection of drawings as input, along with a small number of user‐provided correspondences as input. We register them using a multi‐image matching algorithm, and present them as a 2D interpolation space. By morphing sketches in this space, our approach produces plausible visualizations of shape and viewpoint variations despite the presence of sketch distortions that would prevent standard camera calibration and 3D reconstruction. | en_US |
