Towards Fast and Scalable Normal Integration using Continuous Components
This addresses a fundamental computer vision problem for applications requiring fast surface reconstruction, though it is incremental by building on existing optimization methods.
The paper tackles the slow scalability of surface normal integration by reformulating it as estimating relative scales of continuous components, achieving state-of-the-art results on benchmarks in seconds and a tenfold speedup on large maps.
Surface normal integration is a fundamental problem in computer vision, dealing with the objective of reconstructing a surface from its corresponding normal map. Existing approaches require an iterative global optimization to jointly estimate the depth of each pixel, which scales poorly to larger normal maps. In this paper, we address this problem by recasting normal integration as the estimation of relative scales of continuous components. By constraining pixels belonging to the same component to jointly vary their scale, we drastically reduce the number of optimization variables. Our framework includes a heuristic to accurately estimate continuous components from the start, a strategy to rebalance optimization terms, and a technique to iteratively merge components to further reduce the size of the problem. Our method achieves state-of-the-art results on the standard normal integration benchmark in as little as a few seconds and achieves one-order-of-magnitude speedup over pixel-level approaches on large-resolution normal maps.