The partition technique for overlays of envelopes

We obtain a near-tight bound of O(n(3+epsilon)) for any epsilon > 0 on the complexity of the overlay of the minimization diagrams of two collections of surfaces in four dimensions. This settles a long-standing problem in the theory of arrangements, most recently cited by Agarwal and Sharir [ in Handbook of Computational Geometry, North-Holland, Amsterdam, 2000, pp. 49-119, Open Problem 2], and substantially improves and simplifies a result previously published by the authors [ in Proceedings of the 13th ACM-SIAM Symposium on Discrete Algorithms, ACM, New York, SIAM, Philadelphia, 2002, pp. 810-819]. Our bound is obtained by introducing a new approach to the analysis of combinatorial structures arising in geometric arrangements of surfaces. This approach, which we call the "partition technique," is based on k-fold divide and conquer, in which a given collection F of n surfaces is partitioned into k subcollections F-i of n/k surfaces each, and the complexity of the relevant combinatorial structure in F is recursively related to the complexities of the corresponding structures in each of the F-i's. We introduce this approach by applying it first to obtain a new simple proof for the known near-quadratic bound on the complexity of an overlay of two minimization diagrams of collections of surfaces in R-3, thereby simplifying the previously available proof [ P. K. Agarwal, O. Schwarzkopf, and M. Sharir, Discrete Comput. Geom., 15 (1996), pp. 1-13]. The main new bound on overlays has numerous algorithmic and combinatorial applications, some of which are presented in this paper.