BEGIN:VCALENDAR VERSION:2.0 PRODID:-//CAIL//Events//EN CALSCALE:GREGORIAN METHOD:PUBLISH X-WR-CALNAME:CAIL Events BEGIN:VEVENT UID:2026-07-31-sarah-jobalia@cail.columbia.edu DTSTAMP:20260823T060917Z DTSTART:20260731T150000Z DTEND:20260731T160000Z SUMMARY:Vision Seminar: Sarah Jobalia - HairFlow: A Framework for Creating \, Editing\, and Inferencing Diverse and Feature-Rich Hair Strands LOCATION:CSB 480 DESCRIPTION:How we encode virtual 3D data\, especially in cases of generat ive AI\, can either restrict or facilitate diversity and realism. Ideal en codings capture the social richness of our experience as well as the physi cal realities of our world. These representations are particularly importa nt in the case of virtual hair\, which is both computationally complex and culturally important to represent faithfully.\n\nDisentangling strand tex ture from style highlights two fundamental but separate aspects of hair\, allowing groom construction that can capture the essence of desired styles . Drawing upon scientific\, artistic\, and cultural expertise\, we define strand texture as the various distinctive patterns formed by forces intern al to a hair strand. We propose a novel taxonomy that encompasses naturall y occurring hair strand textures across all hair types.\n\nFrom this taxon omy\, we build a parametric encoding that is both qualitatively accessible \, allowing users to readily locate their own hair within the parameter sp ace\, and quantitatively precise\, allowing the generation of individual s trands from texture inputs. We demonstrate the effectiveness of this encod ing through a diffusion model that can generate strands matching an input texture with minimal training data. With the aid of this model\, we also b uild a texture-transfer pipeline that can change the hair texture of any i nput hairstyle\, further demonstrating the benefits of disentanglement.\n\ nhttps://cail.columbia.edu/events/2026-07-31-sarah-jobalia URL:https://cail.columbia.edu/events/2026-07-31-sarah-jobalia END:VEVENT END:VCALENDAR