SOURCE-LINKED INTELLIGENCE

Direct Optimization of a 3D Finite-Source Reflector via Neural-Network Parameterization

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

We present a direct optimization method for three-dimensional freeform reflectors that transform the light of a finite-étendue source into a prescribed far-field angular intensity distribution. The reflector profile is represented by a small neural network (a multilayer perceptron), which is trained end-to-end through a differentiable ray-tracing objective. We furthermore parameterize the emission directions in gnomonic coordinates, and show how we use this to ensure that every emitted ray intersects the reflector. At each iteration, the network is converted to a bicubic spline representation

Read original source ↗ Open in workspace

recordType

paper

region

Global