Best Paper Honourable Mention Award at Eurographics 2021
25 May 2021
Postdoctoral researcher Meng Zhang and Professor Niloy J. Mitra, at Smart Geometry Processing Group, together with Duygu Ceylan, Tuanfeng Wang from Adobe Research, won Best Paper Honourable Mention Award at international conference of computer graphics, Eurographics 2021.
Congratulations to Meng Zhang, a postdoctoral researcher and Professor Niloy J. Mitra, at Smart Geometry Processing Group, together with Duygu Ceylan, Tuanfeng Wang from Adobe Research, who won Best Paper Honourable Mention Award at the recent international computer graphics conference; Eurographics 2021, for their paper, “Deep Detail Enhancement for Any Garment”.
Image caption: We present a data-driven approach to synthesize plausible wrinkle details on a coarse garment geometry. Such coarse geometry can be obtained either by running a physically-based simulation on a low resolution version of the garment (a), or by using a skinning-based deformation method (d). Our method can generate fine-scale geometry (b,e) by replacing the expensive simulation process, which, in some cases, are not even currently feasible to setup. For example, high-resolution simulation failed (c) for the blue dress as boundary conditions between the blue dress and the yellow belt were grossly violated. Our method generalizes across garment types, often with different number of patterns, associated parameterization and materials, and undergoing different body motions.
Creating fine garment details requires significant efforts and huge computational resources. In contrast, a coarse shape may be easy to acquire in many scenarios (e.g., via low-resolution physically-based simulation, linear blend skinning driven by skeletal motion, portable scanners). This paper demonstrates how to enhance, in a data-driven manner, rich yet plausible details starting from a coarse garment geometry.
Once the parameterization of the garment is given, the task is formulated as a style transfer problem over the space of associated normal maps. In order to facilitate generalization across garment types and character motions, a patch-based formulation is introduced, that produces high-resolution details by matching a Gram matrix based style loss, to hallucinate geometric details (i.e., wrinkle density and shape). This method is simple, lightweight, efficient, and can be applied across underlying garment types, sewing patterns, and body motion.
To learn more about the 'Deep Detail Enhancement for Any Garment' paper, please visit the project webpage.