A.4 IMPLEMENTATIONDETAILS All the methods are evaluated on a single Nvidia RTX A6000 GPU

The gradient flow PDE ofL veik forp= 2takes the form: du dt =∇ ·((∥∇u∥2 −1) ∥∇u∥2 ∇u) +ε∆ ((∥∇u∥2 −1)∇u) +ε∇(∆u∇u)−ε 2∆(∆u)(34) Linearizing the PDE around the stationary linear solutionu=a·xgives the linear PDE: du dt =∂ 2 x1 u1 +ε∂ x1 (∆u) · 1998

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

browse 1 citing papers

representative citing papers

ViscoReg: Neural Signed Distance Functions via Viscosity Solutions

cs.GR · 2025-07-01 · conditional · novelty 6.0

A viscosity-regularized Eikonal loss with annealed epsilon improves Neural SDF reconstruction and yields the first generalization bound for SDF learning.

citing papers explorer

Showing 1 of 1 citing paper.

ViscoReg: Neural Signed Distance Functions via Viscosity Solutions cs.GR · 2025-07-01 · conditional · none · ref 16
A viscosity-regularized Eikonal loss with annealed epsilon improves Neural SDF reconstruction and yields the first generalization bound for SDF learning.

A.4 IMPLEMENTATIONDETAILS All the methods are evaluated on a single Nvidia RTX A6000 GPU

fields

years

verdicts

representative citing papers

citing papers explorer