Abstract
Viewpoint selection methods have a variety of applications in different fields of computer graphics and computer vision, including shape retrieval, scientific visualization, image-based modeling and others. In this paper we investigate the applicability of existing viewpoint selection methods to the problem of textures reconstruction using inverse rendering. First, we use forward rendering to produce path-traced images of a textured object. Then we apply different view quality metrics to select a set of images for texture reconstruction. Finally, we perform material and texture reconstruction using these image sets and evaluate the quality of the results. We show that using viewpoint selection methods allows to achieve faster inverse rendering times while maintaining quality of the results.
Publisher
Keldysh Institute of Applied Mathematics
Reference21 articles.
1. S. Zhao, W. Jakob, T.-M. Li, Physics-based differentiable rendering: from theory to implementation, in: ACM siggraph 2020 courses, 2020, pp. 1–30. doi:10.1145/3388769.3407454.
2. S. Zhao, F. Luan, K. Bala, Fitting procedural yarn models for realistic cloth rendering, ACM Transactions on Graphics (TOG) 35 (2016) 1–11. doi:10.1145/2897824.2925932.
3. Z. Zhou, G. Chen, Y. Dong, D. Wipf, Y. Yu, J. Snyder, X. Tong, Sparse-as-possible svbrdf acquisition, ACM Transactions on Graphics (TOG) 35 (2016) 1–12. doi:10.1145/2980179.2980247.
4. W. Jakob, S. Speierer, N. Roussel, M. Nimier-David, D. Vicini, T. Zeltner, B. Nicolet, M. Crespo, V. Leroy, Z. Zhang, Mitsuba 3 renderer, 2023. URL: https://mitsuba-renderer.org.
5. X. Bonaventura, M. Feixas, M. Sbert, L. Chuang, C. Wallraven, A survey of viewpoint selection methods for polygonal models, Entropy 20 (2018) 370. doi:10.3390/e20050370.