Results 231 to 240 of about 25,572 (317)

Edge‐preserving noise for diffusion models

Computer 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, Sascha Holl, Xingchang Huang, Gurprit Singh   +3 more
wiley   +1 more source

On Hodge polynomials for nonalgebraic complex manifolds. [PDF]

Proc Natl Acad Sci U S A
Katzarkov L, Lee KS, Lupercio E, Meersseman L.   +3 more
europepmc   +1 more source

Progressively Projected Newton's Method

Computer Graphics Forum, EarlyView.
Abstract Newton's Method is widely used to find the solution of complex non‐linear simulation problems. To guarantee a descent direction, it is common practice to clamp the negative eigenvalues of each element Hessian prior to assembly—a strategy known as Projected Newton (PN)—but this perturbation often hinders convergence.
J. A. Fernández‐Fernández, F. Löschner, J. Bender   +2 more
wiley   +1 more source

Gas Turbine Blade Characterization Through Modal Analysis. [PDF]

Materials (Basel)
Troglia Gamba A, Bagnera F, Botto D.
europepmc   +1 more source

Survey on differential estimators for 3d point clouds

Computer Graphics Forum, EarlyView.
Abstract Recent advancements in 3D scanning technologies, including LiDAR and photogrammetry, have enabled the precise digital replication of real‐world objects. These methods are widely used in fields such as GIS, robotics, and cultural heritage. However, the point clouds generated by such scans are often noisy and unstructured, posing challenges for ...
Léo Arnal–Anger, Thibault Lejemble, David Coeurjolly, Loïc Barthe, Nicolas Mellado   +4 more
wiley   +1 more source

Beyond Euclid: an illustrated guide to modern machine learning with geometric, topological, and algebraic structures. [PDF]

Mach Learn Sci Technol
Papillon M, Sanborn S, Mathe J, Cornelis L, Bertics A, Buracas D, J Lillemark H, Shewmake C, Dinc F, Pennec X, Miolane N.   +10 more
europepmc   +1 more source

Register‐Efficient Linear‐Time Evaluation in the Bernstein Basis

Computer Graphics Forum, EarlyView.
Abstract We investigate the evaluation of points and derivatives of Bézier curves and surfaces on modern architectures, focusing on performance and guided by numerical error bounds. While the de Casteljau algorithm remains the reference for numerical robustness, its linear working‐set size imposes substantial register pressure on GPUs.
Gábor Valasek, Anna Lili Horváth
wiley   +1 more source

Evaluating Pancreatic Cancer Treatment Strategies Using a Novel Polytopic Fuzzy Tensor Approach. [PDF]

Bioengineering (Basel)
Bilal M, Li C, Alzahrani AK, Aljahdali AK.   +3 more
europepmc   +1 more source

Hierarchical Optimization of the As‐Rigid‐As‐Possible Energy

Computer Graphics Forum, EarlyView.
Abstract The As‐Rigid‐As‐Possible (ARAP) energy [SA07] has become a versatile ingredient in various geometry processing and machine learning methods. The classic method for its minimization is a block coordinate descent, alternating between local rotation estimation and a global linear solve, which converges slowly for large problem instances.
Hendrik Meyer, Bernd Bickel, Marc Alexa
wiley   +1 more source

Quadratic Subproduct Systems, Free Products, and Their C*-Algebras. [PDF]

Integr Equ Oper Theory
Arici F, Ge Y.
europepmc   +1 more source