Results 141 to 150 of about 10,375 (259)

OUGS: Active View Selection via Object‐aware Uncertainty Estimation in 3DGS

open access: yesComputer Graphics Forum, EarlyView.
Abstract Recent advances in 3D Gaussian Splatting (3DGS) have achieved state‐of‐the‐art results for novel view synthesis. However, efficiently capturing high‐fidelity reconstructions of specific objects within complex scenes remains a significant challenge.
Haiyi Li   +3 more
wiley   +1 more source

Interpolated Adaptive Linear Reduced Order Modeling for Deformation Dynamics

open access: yesComputer Graphics Forum, EarlyView.
Abstract Linear reduced‐order modeling (ROM) is widely used for efficient simulation of deformation dynamics, but its accuracy is often limited by the fixed linearization of the reduced mapping. We propose a new adaptive strategy for linear ROM that allows the reduced mapping to vary dynamically in response to the evolving deformation state ...
Y. Tao, M. Chiaramonte, P. Fernandez
wiley   +1 more source

Affinification: A Fine Approximation of Deformations

open access: yesComputer Graphics Forum, EarlyView.
Abstract We introduce affinification, a novel method for accelerating physics‐based animation of elastic solids. During a time‐dependent simulation, our method automatically partitions the space into affine and elastic regions depending on the deformation.
A. Mercier‐Aubin   +3 more
wiley   +1 more source

Skeletal‐Driven Animation of Anatomical Humans via Neural Deformation Gradients

open access: yesComputer Graphics Forum, EarlyView.
Abstract Most real‐time animation techniques for digital humans are limited to deforming the outer skin surface. Geometric skinning methods are highly efficient but struggle with artifacts such as collapsing joints or self‐intersections when animating inner anatomy along with the outer skin.
G. Nolte   +3 more
wiley   +1 more source

Stochastic Pairwise MIS for Unbiased Large‐Kernel Reuse in Real‐Time

open access: yesComputer Graphics Forum, EarlyView.
Abstract Spatiotemporal resampling methods such as ReSTIR decrease noise in Monte Carlo rendering of dynamic content by reusing paths across frames and pixels. Standard ReSTIR reuses spatially from a small number of randomly selected neighbors. This reuse suffers when few neighbors contain contributing samples, reducing quality toward that of the ...
Trevor Hedstrom   +4 more
wiley   +1 more source

Home - About - Disclaimer - Privacy