Results 241 to 250 of about 1,722,948 (307)

Edge‐preserving noise for diffusion models

open access: yesComputer Graphics Forum, EarlyView.
Abstract Classical diffusion models typically rely on isotropic Gaussian noise, treating all regions uniformly and overlooking structural information important for high‐quality generation. We introduce an edge‐preserving diffusion process that generalizes isotropic models via a hybrid noise scheme with an edge‐aware scheduler that smoothly transitions ...
Jente Vandersanden   +3 more
wiley   +1 more source

Establishing Shape Correspondences: A Survey

open access: yesComputer Graphics Forum, EarlyView.
Abstract Shape correspondence between surfaces in 3D is a central problem in geometry processing, concerned with establishing meaningful relations between surfaces. While all correspondence problems share this goal, specific formulations can differ significantly: Downstream applications require certain properties that correspondences must satisfy ...
A. Heuschling, H. Meinhold, L. Kobbelt
wiley   +1 more source

A Cyber-Physical Digital Twin Framework for State Estimation of Dendrite-Risk Prediction and Resilient Control in Solid-State Batteries. [PDF]

open access: yesGlob Chall
Subramanian S   +8 more
europepmc   +1 more source

Differentiable Randers‐Finsler Eikonal Solvers

open access: yesComputer Graphics Forum, EarlyView.
Abstract Fast and differentiable solvers for anisotropic and asymmetric distance fields are a key primitive in geometry processing, enabling gradient‐based optimization over metrics, drift fields, and downstream objectives that depend on geodesic distances and geodesics.
Barak Gahtan   +2 more
wiley   +1 more source

Anomalous charge density wave in a two-dimensional superatomic superconductor. [PDF]

open access: yesNat Commun
Song B   +14 more
europepmc   +1 more source

On Bending in the As‐Rigid‐As‐Possible Deformation Energy

open access: yesComputer Graphics Forum, EarlyView.
Abstract The well‐established As‐Rigid‐As‐Possible (ARAP) energy has various forms. For surface deformation, commonly used energies contain an implicit bending penalty. We present a natural, continuous generalization that incorporates multiple ARAP versions with an implicit, user‐controllable bending penalty.
Ugo Finnendahl, Marc Alexa
wiley   +1 more source

Strictly Conservative Neural Distance Fields

open access: yesComputer Graphics Forum, EarlyView.
Abstract We propose a first method to generate neural unsigned or signed distance fields (SDFs) that are guaranteed to be conservative with respect to a given 3D shape. This means the true distance is never overestimated and the zero‐level set is a bounding volume for the shape. The method makes use of neural network architectures that ensure Lipschitz
I. Ludwig, M. Campen
wiley   +1 more source

Home - About - Disclaimer - Privacy