We present HRM2Avatar, a novel framework for creating high-fidelity avatars from monocular phone scans, which can be rendered and animated in real-time on mobile devices. Monocular capture with commodity smartphones provides a low-cost, pervasive alternative to studio-grade multi-camera rigs, making avatar digitization accessible to non-expert users. Reconstructing high-fidelity avatars from single-view video sequences poses significant challenges due to deficient visual and geometric data relative to multi-camera setups. To address these limitations, at the data level, our method leverages two types of data captured with smartphones: static pose sequences for detailed texture reconstruction and dynamic motion sequences for learning pose-dependent deformations and lighting changes. At the representation level, we employ a lightweight yet expressive representation to reconstruct high-fidelity digital humans from sparse monocular data. First, we extract explicit garment meshes from monocular data to model clothing deformations more effectively. Second, we attach illumination-aware Gaussians to the mesh surface, enabling high-fidelity rendering and capturing pose-dependent lighting changes. This representation efficiently learns high-resolution and dynamic information from our tailored monocular data, enabling the creation of detailed avatars. At the rendering level, real-time performance is critical for rendering and animating high-fidelity avatars in AR/VR, social gaming, and on-device creation, demanding sub-frame responsiveness. Our fully GPU-driven rendering pipeline delivers 120 FPS on mobile devices and 90 FPS on standalone VR devices at 2K resolution, over 2.7 × faster than representative mobile-engine baselines. Experiments show that HRM2Avatar delivers superior visual realism and real-time interactivity at high resolutions, outperforming state-of-the-art monocular methods.

This paper aims to instantly predict within any accuracy the stress distribution of cellular structures under parametric design, including the shapes or distributions of the cell geometries, or the magnitudes of external loadings. A classical model reduction technique has to balance the simulation accuracy and interaction speed, and has difficulty achieving this goal. We achieve this by computing offline a design-to-stress mapping that ultimately expresses the stress distribution as an explicit function in terms of its design parameters. The mapping is determined as a solution to an extended finite element analysis problem in a high-dimension space, including both the spatial coordinates and the design parameters. The well-known curse of dimensionality intrinsic to the high-dimension problem is (partly) resolved through a spatial separation using two main techniques. First, the target mapping takes a reduced form as a sum of the products of separated one-variable functions, extending the proper generalized decomposition technique. Second, the simulation problem in a varied computation domain is reformulated as that in a fixed-domain, taking an integration function as the sum of the products of separated one-variable functions, in combination with high-order singular value decomposition. Extensive 2D and 3D examples are shown to demonstrate the approach’s performance.