Reconstructing a triangular mesh from images by a differentiable rendering framework often exploits discrete Laplacians on the mesh, e.g., the cotangent Laplacian, so that a stochastic gradient descent-based optimization in the framework can become stable by a regularization term formed with the Laplacians. However, the stability stemming from using such a regularizer often comes at the cost of over-smoothing a resulting mesh, especially when the Laplacian of the mesh is not properly approximated, e.g., too-noisy or overly-smoothed Laplacian of the mesh. This paper presents a new discrete Laplacian built upon a kernel-weighted Laplacian. We control the kernel weights using a local bandwidth parameter so that the geometry optimization in a differentiable rendering framework can be improved by avoiding blurring high-frequency details of a surface. We demonstrate that our discrete Laplacian with a local adaptivity can improve the quality of reconstructed meshes and convergence speed of the geometry optimization by plugging our discrete Laplacian into recent differentiable rendering frameworks.
This is a preview of subscription content,to check access.
Access this article
We use publicly available data (see the information on tested 3D models in the acknowledgments), and our source code will be available at https://github.com/CGLab-GIST/awl.
Belkin, M., Sun, J., Wang, Y.: Discrete laplace operator on meshed surfaces. In: Proceedings of the Twenty-Fourth Annual Symposium on Computational Geometry, SCG ’08, p. 278-287. Association for Computing Machinery, USA (2008)
Community, B.O.: Blender - a 3D modelling and rendering package. Blender Foundation, Stichting Blender Foundation, Amsterdam (2018). http://www.blender.org
Dziuk, G.: Finite Elements for the Beltrami operator on arbitrary surfaces. Springer, Berlin (1988)
Kazhdan, M., Solomon, J., Ben-Chen, M.: Can mean-curvature flow be modified to be non-singular? Comput. Graph. Forum 31(5), 1745–1754 (2012)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Luan, F., Zhao, S., Bala, K., Dong, Z.: Unified shape and svbrdf recovery using differentiable monte carlo rendering. Comput. Graph. Forum 40(4), 101–113 (2021)
Nealen, A., Igarashi, T., Sorkine, O., Alexa, M.: Laplacian mesh optimization. In: Proceedings of the 4th International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia, GRAPHITE ’06, p. 381-389. Association for Computing Machinery, USA (2006)
Nicolet, B., Jacobson, A., Jakob, W.: Large steps in inverse rendering of geometry. ACM Trans. Graph. 40(6), 1–13 (2021)
Palfinger, W.: Continuous remeshing for inverse rendering. Comput. Animation Virt. Worlds 33(5), e2101 (2022)
Pinkall, U., Polthier, K.: Computing discrete minimal surfaces and their conjugates. Exp. Math. 2(1), 15–36 (1993)
Sharp, N., Crane, K.: A Laplacian for nonmanifold triangle meshes. Comput. Graph. Forum 39(5), 69–80 (2020)
Wand, M.P., Jones, M.C.: Kernel Smoothing. CRC press (1994)
Wang, N., Zhang, Y., Li, Z., Fu, Y., Liu, W., Jiang, Y.G.: Pixel2mesh: Generating 3d mesh models from single rgb images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Comput Vis - ECCV 2018, pp. 55–71. Springer International Publishing, Cham (2018)
Wardetzky, M., Mathur, S., Kaelberer, F., Grinspun, E.: Discrete Laplace operators: No free lunch. In: A. Belyaev, M. Garland (eds.) Geometry Processing. The Eurographics Association (2007)
We appreciate the reviewers for their helpful comments and thank the following providers of the tested 3D models: Stanford 3D repository (Armadillo, Bunny, Lucy), Oliver Laric (Dark-finger-reef-crab, Elbo-crab), Smithsonian National Museum of Natural History (Cranium), yeg3d (Deer), and Natural History Museum Vienna (Smilodon).
This work was supported in part by Ministry of Culture, Sports and Tourism and Korea Creative Content Agency (No. R2021080001) and by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2022-0-00566).
Conflicts of interest
We do not have a conflict of interest.
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Below is the link to the electronic supplementary material.
Supplementary file 1 (mp4 72725 KB)
About this article
Cite this article
An, H., Lee, W. & Moon, B. Adaptively weighted discrete Laplacian for inverse rendering. Vis Comput 39, 3211–3220 (2023). https://doi.org/10.1007/s00371-023-02955-2