Presentation

<
MaterialPicker: Multi-Modal DiT-Based Material Generation
SessionBeautiful Materials
DescriptionMaterialPicker is a multi-modal material generation model that creates high-quality material maps from images and/or text by fine-tuning a video diffusion model. It robustly extracts materials from real-world photos, even with distortion or occlusion, enhancing fidelity, diversity, and efficiency in material synthesis.
Authors
Xiaohe Ma
State Key Lab of CAD&CG, Zhejiang University
Valentin Deschaintre
Adobe Research
Milos Hasan
Adobe Research
Fujun Luan
Adobe Research
Kun Zhou
State Key Lab of CAD&CG, Zhejiang University
ZJU-FaceUnity Joint Lab of Intelligent Graphics
Hongzhi Wu
State Key Lab of CAD&CG, Zhejiang University
Yiwei Hu
Adobe Research
Event Type
Technical Paper
TimeThursday, 14 August 20259:00am - 9:10am PDT
LocationWest Building, Rooms 301-305
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Thursday, 14 August 20259:00am - 10:30am PDTWest Building, Rooms 301-305
Recordings
Livestreamed
Recorded
Next PresentationNext PresentationMatCLIP: Light- and Shape-Insensitive Assignment of PBR Material Models
Similar Presentations
Generative Neural Materials
A Fluorescent Material Model for Non-Spectral Editing & Rendering
MatCLIP: Light- and Shape-Insensitive Assignment of PBR Material Models