Uploaded May 2021 | Updated November 2026, 20 minutes ago
By Margarita Grinvald, Federico Tombari, Roland Siegwart, and Juan Nieto.
Abstract - The ability to simultaneously track and reconstruct multiple objects moving in the scene is of the utmost importance for robotic tasks such as autonomous navigation and interaction. Virtually all of the previous attempts to map multiple dynamic objects have evolved to store individual objects in separate reconstruction volumes and track the relative pose between them. While simple and intuitive, such formulation does not scale well with respect to the number of objects in the scene and introduces the need for an explicit occlusion handling strategy. In contrast, we propose a map representation that allows maintaining a single volume for the entire scene and all the objects therein. To this end, we introduce a novel multi-object TSDF formulation that can encode multiple object surfaces at any given location in the map. In a multiple dynamic object tracking and reconstruction scenario, our representation allows maintaining accurate reconstruction of surfaces even while they become temporarily occluded by other objects moving in their proximity. We evaluate the proposed TSDF++ formulation on a public synthetic dataset and demonstrate its ability to preserve reconstructions of occluded surfaces when compared to the standard TSDF map representation.
The paper has been accepted to the 2021 IEEE International Conference on Robotics and Automation (ICRA) in Xi'an, China.
Paper: arxiv.org/abs/2105.07468
Code: github.com/ethz-asl/tsdf-plusplus
By Margarita Grinvald, Federico Tombari, Roland Siegwart, and Juan Nieto.
Abstract - The ability to simultaneously track and reconstruct multiple objects moving in the scene is of the utmost importance for robotic tasks such as autonomous navigation and interaction. Virtually all of the previous attempts to map multiple dynamic objects have evolved to store individual objects in separate reconstruction volumes and track the relative pose between them. While simple and intuitive, such formulation does not scale well with respect to the number of objects in the scene and introduces the need for an explicit occlusion handling strategy. In contrast, we propose a map representation that allows maintaining a single volume for the entire scene and all the objects therein. To this end, we introduce a novel multi-object TSDF formulation that can encode multiple object surfaces at any given location in the map. In a multiple dynamic object tracking and reconstruction scenario, our representation allows maintaining accurate reconstruction of surfaces even while they become temporarily occluded by other objects moving in their proximity. We evaluate the proposed TSDF++ formulation on a public synthetic dataset and demonstrate its ability to preserve reconstructions of occluded surfaces when compared to the standard TSDF map representation.
The paper has been accepted to the 2021 IEEE International Conference on Robotics and Automation (ICRA) in Xi'an, China.
Paper: arxiv.org/abs/2105.07468
Code: github.com/ethz-asl/tsdf-plusplus
![[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)









