Uploaded January 2018 | Updated November 2026, 19 minutes ago
Accompanying video for our RA-L 2018 publication titled "Incremental Segment-Based Localization in 3D Point Clouds": ieeexplore.ieee.org/abstract/document/8283725
The system is available open source and easy-to-run demonstrations are publicly available at github.com/ethz-asl/segmap
Abstract— Localization in 3D point clouds is a highly challenging task due to the complexity associated with extracting information from 3D data. This paper proposes an incremental approach addressing this problem efficiently. The presented method first accumulates the measurements in a dynamic voxel grid and selectively updates the point normals affected by the insertion. An incremental segmentation algorithm, based on region growing, tracks the evolution of single segments which enables an efficient recognition strategy using partitioning and caching of geometric consistencies. We show that the incremental method can perform global localization at 10Hz in a urban driving environment, a speedup of x7.1 over the compared batch solution. The efficiency of the method makes it suitable for applications where real-time localization is required and enables its usage on cheaper, low-energy systems. Our implementation will be available open source after publication along with instructions for running the system.
Related videos:
youtu.be/CMk4w4eRobg
youtube.com/watch?v=iddCgYbgpjE youtube.com/watch?v=JJhEkIA1xSE
Contact: renaudube(at)gmail.com and gollubm(at)ethz.ch
Accompanying video for our RA-L 2018 publication titled "Incremental Segment-Based Localization in 3D Point Clouds": ieeexplore.ieee.org/abstract/document/8283725
The system is available open source and easy-to-run demonstrations are publicly available at github.com/ethz-asl/segmap
Abstract— Localization in 3D point clouds is a highly challenging task due to the complexity associated with extracting information from 3D data. This paper proposes an incremental approach addressing this problem efficiently. The presented method first accumulates the measurements in a dynamic voxel grid and selectively updates the point normals affected by the insertion. An incremental segmentation algorithm, based on region growing, tracks the evolution of single segments which enables an efficient recognition strategy using partitioning and caching of geometric consistencies. We show that the incremental method can perform global localization at 10Hz in a urban driving environment, a speedup of x7.1 over the compared batch solution. The efficiency of the method makes it suitable for applications where real-time localization is required and enables its usage on cheaper, low-energy systems. Our implementation will be available open source after publication along with instructions for running the system.
Related videos:
youtu.be/CMk4w4eRobg
youtube.com/watch?v=iddCgYbgpjE youtube.com/watch?v=JJhEkIA1xSE
Contact: renaudube(at)gmail.com and gollubm(at)ethz.ch





![[WACV 2026] Towards Fast and Scalable Normal Integration using Continuous Components
This is the accompanying video of our WACV 2026 paper Towards Fast and Scalable Normal Integration using Continuous Components.
Paper: https://arxiv.org/abs/2510.11508
Code: https://github.com/francescomilano172/normal_integration_continuous_components
Abstract:
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.
Reference:
Francesco Milano, Jen Jen Chung, Lionel Ott, Roland Siegwart, Towards Fast and Scalable Normal Integration using Continuous Components, IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026.
Affiliations:
Autonomous Systems Laboratory, ETH Zurich.
The University of Queensland. [WACV 2026] Towards Fast and Scalable Normal Integration using Continuous Components](https://i.ytimg.com/vi/dZQAswCNM2E/mqdefault.jpg)




