# End-to-end Surface Optimization for Light Control

arXiv: https://arxiv.org/abs/2408.13117 · HTML: https://mlsanity.com/paper/2408.13117/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 47 references that are in the map.
- First posted on arXiv 23 Aug 2024.

## Builds on (most cited first, 4 of 4)

- [Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning](https://mlsanity.com/paper/1904.01786/) (2019)
- [Fast and Robust Iterative Closest Point](https://mlsanity.com/paper/2007.07627/) (2020)
- [Light in Power: A General and Parameter-free Algorithm for Caustic Design](https://mlsanity.com/paper/1708.04820/) (2017)
- [Stealth Shaper: Reflectivity Optimization as Surface Stylization](https://mlsanity.com/paper/2305.05944/) (2023)

## Built on by (most cited first, 1 of 1)

- [Direct Optimization of a 3D Finite-Source Reflector via Neural-Network Parameterization](https://mlsanity.com/paper/2609.00899/) (2026)

## Abstract (arXiv)

Designing a freeform surface to reflect or refract light to achieve a target distribution is a challenging inverse problem. In this paper, we propose an end-to-end optimization strategy for an optical surface mesh. Our formulation leverages a novel differentiable rendering model, and is directly driven by the difference between the resulting light distribution and the target distribution. We also enforce geometric constraints related to fabrication requirements, to facilitate CNC milling and polishing of the designed surface. To address the issue of local minima, we formulate a face-based optimal transport problem between the current mesh and the target distribution, which makes effective large changes to the surface shape. The combination of our optimal transport update and rendering-guided optimization produces an optical surface design with a resulting image closely resembling the target, while the geometric constraints in our optimization help to ensure consistency between the rendering model and the final physical results. The effectiveness of our algorithm is demonstrated on a variety of target images using both simulated rendering and physical prototypes.