Loading patent…
AssigneeNVIDIA Corporation
InventorsCarl Jacob Munkberg, Jon Niklas Theodor Hasselgren, Zian Wang, Tianchang Shen, Ruofan Liang
Estimating the term…
Systems and methods are disclosed that extracting material information using one or more video diffusion models. For example, embodiments of the present disclosure may process one or more images and a text prompt using a first video diffusion model to generate a rendered video of an object. For instance, the one or more images may be based on a three-dimensional (3D) geometry of the object and lighting conditions and the rendered image may include frames that show different viewpoints of the object. Subsequently, a differentiable renderer may be used to process the rendered video to generate a material data structure for the object, which indicates material information for points from the 3D geometry of the object. The material information may indicate physical-based rendering (PBR) characteristics such as an albedo, roughness, and/or metallic characteristic of the points on the object.
A computer-implemented method for extracting material information using one or more video diffusion models, comprising:
A system for extracting material information using one or more video diffusion models, comprising:
A non-transitory computer-readable medium having processor-executable instructions stored thereon for extracting material information using one or more video diffusion models, wherein the processor-executable instructions, when executed, facilitate:
Dependencies are inferred from the claim text.