Recreating Real Garments in Virtual Space with Gaussian Splatting and GNNs (Talk)
Recent advances in scene reconstruction with 3D Gaussian Splatting and cloth simulation with Graph neural networks open the prospects for methods that reconstruct proto-realistic virtual garments from visual observations. In this talk we will present our recently submitted paper – Gaussian Garments. There we reconstruct simulation ready photorealistic garments from multi-view videos. With the power of 3D Gaussian Splatting we are able to match three key aspects of real garments in virtual space: their geometry, appearance and behavior. The resulting virtual garments can then be combined into complex outfits, automatically resized and simulated in dynamic scenes.
Biography: Boxiang Rong is a master’s student in the department of Mechanical and Process Engineering at ETH Zurich. Under the supervision of PS PhD student Artur Grigorev he participated in writing 4D-Dress paper, accepted to CVPR 2024 and then led the project for Gaussian Garments paper currently under review at a major conference.
