During interactive segmentation, a model and a user work together to delineate objects of interest in a 3D point cloud. In an iterative process, the model assigns each data point to an object (or the background), while the user corrects errors in the resulting segmentation and feeds them back into the model. The current best practice formulates the problem as binary classification and segments objects one at a time. The model expects the user to provide positive clicks to indicate regions wrongly assigned to the background and negative clicks on regions wrongly assigned to the object. Sequentially visiting objects is wasteful since it disregards synergies between objects: a positive click for a given object can, by definition, serve as a negative click for nearby objects. Moreover, a direct competition between adjacent objects can speed up the identification of their common boundary. We introduce AGILE3D, an efficient, attention-based model that (1) supports simultaneous segmentation of multiple 3D objects, (2) yields more accurate segmentation masks with fewer user clicks, and (3) offers faster inference. Our core idea is to encode user clicks as spatial-temporal queries and enable explicit interactions between click queries as well as between them and the 3D scene through a click attention module. Every time new clicks are added, we only need to run a lightweight decoder that produces updated segmentation masks. In experiments with four different 3D point cloud datasets, AGILE3D sets a new state-of-the-art. Moreover, we also verify its practicality in real-world setups with real user studies. Project page: https://ywyue.github.io/AGILE3D.

We address 2D floorplan reconstruction from 3D scans. Existing approaches typically employ heuristically designed multi-stage pipelines. Instead, we formulate floor-plan reconstruction as a single-stage structured prediction task: find a variablesize set of polygons, which in turn are variable-length sequences of ordered vertices. To solve it we develop a novel Transformer architecture that generates polygons of multiple rooms in parallel, in a holistic manner without hand-crafted intermediate stages. The model features two-level queries for polygons and corners, and includes polygon matching to make the network end-to-end trainable. Our method achieves a new state-of-the-art for two challenging datasets, Structured3D and SceneCAD, along with significantly faster inference than previous methods. Moreover, it can readily be extended to predict additional information, i.e., semantic room types and architectural elements like doors and windows. Our code and models are available at: https://github.com/ywyue/RoomFormer.

Accurate and rapid detection and mapping of guardrails play an essential role in road maintenance, asset management, and safety audits. This paper proposes an automated approach for guardrail detection and mapping in rural highway environments from mobile laser scanning point clouds. First, the scanning vehicle trajectory is extracted, and a buffer zone is constructed to remove points far from the roadside. Then multiple geometric filters and statistical outlier removal are applied to find the candidate guardrail points. The verticality of each point is calculated to further refine the detection. Next, a density-based clustering algorithm is used to group the remaining points into clusters. Finally, the detected guardrails are plotted on Google Earth to create an inventory map. Experiments on three rural highways demonstrate that the proposed algorithm can detect and map guardrails automatically with high accuracy.