# An Adaptive Screen-Space Meshing Approach for Normal Integration

arXiv: https://arxiv.org/abs/2409.16907 · HTML: https://mlsanity.com/paper/2409.16907/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 38 references that are in the map.
- First posted on arXiv 25 Sep 2024.

## Builds on (most cited first, 6 of 6)

- [Modular Primitives for High-Performance Differentiable Rendering](https://mlsanity.com/paper/2011.03277/) (2020)
- [Towards Layer-wise Image Vectorization](https://mlsanity.com/paper/2206.04655/) (2022)
- [Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materials](https://mlsanity.com/paper/2001.06659/) (2020)
- [Normal Integration: A Survey](https://mlsanity.com/paper/1709.05940/) (2017)
- [Image Vectorization: a Review](https://mlsanity.com/paper/2306.06441/) (2023)
- [Least squares surface reconstruction on arbitrary domains](https://mlsanity.com/paper/2007.08661/) (2020)

## Built on by (most cited first, 7 of 7)

- [Feature-Preserving Mesh Decimation for Normal Integration](https://mlsanity.com/paper/2504.00867/) (2025)
- [Discontinuity-aware Normal Integration for Generic Central Camera Models](https://mlsanity.com/paper/2507.06075/) (2025)
- [Towards Fast and Scalable Normal Integration using Continuous Components](https://mlsanity.com/paper/2510.11508/) (2025)
- [EvalMVX: A Unified Benchmarking for Neural 3D Reconstruction under Diverse Multiview Setups](https://mlsanity.com/paper/2602.24065/) (2026)
- [High-fidelity Multi-view Normal Integration with Scale-encoded Neural Surface Representation](https://mlsanity.com/paper/2603.20337/) (2026)
- [PixVOD: Pixel-Distributed Direct Visual Odometry and Depth Estimation](https://mlsanity.com/paper/2606.03989/) (2026)
- [FlashNormal: Detailed Surface Normal Estimation from Flash and No-Flash Images](https://mlsanity.com/paper/2608.25360/) (2026)

## Abstract (arXiv)

Reconstructing surfaces from normals is a key component of photometric stereo. This work introduces an adaptive surface triangulation in the image domain and afterwards performs the normal integration on a triangle mesh. Our key insight is that surface curvature can be computed from normals. Based on the curvature, we identify flat areas and aggregate pixels into triangles. The approximation quality is controlled by a single user parameter facilitating a seamless generation of low- to high-resolution meshes. Compared to pixel grids, our triangle meshes adapt locally to surface details and allow for a sparser representation. Our new mesh-based formulation of the normal integration problem is strictly derived from discrete differential geometry and leads to well-conditioned linear systems. Results on real and synthetic data show that 10 to 100 times less vertices are required than pixels. Experiments suggest that this sparsity translates into a sublinear runtime in the number of pixels. For 64 MP normal maps, our meshing-first approach generates and integrates meshes in minutes while pixel-based approaches require hours just for the integration.