Problem
Research questions and friction points this paper is trying to address.
3D Freeform Reflectors
Finite-Source
Angular Intensity Distribution
Direct Optimization of a 3D Finite-Source Reflector via Neural-Network Parameterization
🤖 AI Summary
该研究提出了一种直接优化方法，通过神经网络参数化3D自由曲面反射器，将有限光源转化为指定的远场角强度分布。
📝 Abstract
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 for ray-tracing efficiency, and intersections with this smooth surface are solved by a damped Newton solve, with gradients computed via the implicit function theorem. The traced output distribution is compared with the desired target on a 'soft' histogram, under an $H^{-1}$-type spectral weighting that emphasizes long-range transport of flux to improve convergence. Optimization is performed using a BFGS method with self-scaled Broyden updates and a plateau-perturbation rule to prevent stalling. The method converges reliably within seconds on a single GPU for all examples tested.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Neural-Network Parameterization
Differentiable Ray-Tracing
Gnomonic Coordinates
Bicubic Spline Representation
H^-1 Spectral Weighting
🔎 Similar Papers
No similar papers found.
