Neural networks with change-of-variables and mesh-based losses outperform a deconvolution baseline in accuracy and speed for 2D finite-source reflector design on four benchmarks.
Using machine learning to create high-efficiency freeform illumination design tools
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present a method for improving the efficiency and user experience of freeform illumination design with machine learning. By utilizing orthogonal polynomials to interface with artificial neural networks, we are able to generalize relationships between freeform surface shapes and design parameters. Then, by training the network to generalize the relationship between high-level design goals and final performance, we were able to transform what is traditionally a difficult and computationally intensive problem into a compact, user friendly form. The potential of the proposed method is demonstrated through the design of uniform square patterns from off-axis positions and rectangular patterns of tuneable aspect ratios and distances from the target.
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neural-network methods for two-dimensional finite-source reflector design
Neural networks with change-of-variables and mesh-based losses outperform a deconvolution baseline in accuracy and speed for 2D finite-source reflector design on four benchmarks.