# RoEL: Robust Event-based 3D Line Reconstruction Source: [RoEL: Robust Event-based 3D Line Reconstruction]() Collection index: [llms.txt]() Data updated: 2026-02-24T05:00:04.779Z Authors: Gwangtak Bae, Jaeho Shin, Seunggu Kang, Junho Kim, Ayoung Kim, Young Min Kim Published: 2026-02-20T14:43:46.000Z ## Abstract Event cameras in motion tend to detect object boundaries or texture edges, which produce lines of brightness changes, especially in man-made environments. While lines can constitute a robust intermediate representation that is consistently observed, the sparse nature of lines may lead to drastic deterioration with minor estimation errors. Only a few previous works, often accompanied by additional sensors, utilize lines to compensate for the severe domain discrepancies of event sensors along with unpredictable noise characteristics. We propose a method that can stably extract tracks of varying appearances of lines using a clever algorithmic process that observes multiple representations from various time slices of events, compensating for potential adversaries within the event data. We then propose geometric cost functions that can refine the 3D line maps and camera poses, eliminating projective distortions and depth ambiguities. The 3D line maps are highly compact and can be equipped with our proposed cost function, which can be adapted for any observations that can detect and extract line structures or projections of them, including 3D point cloud maps or image observations. We demonstrate that our formulation is powerful enough to exhibit a significant performance boost in event-based mapping and pose refinement across diverse datasets, and can be flexibly applied to multimodal scenarios. Our results confirm that the proposed line-based formulation is a robust and effective approach for the practical deployment of event-based perceptual modules. Project page: https://gwangtak.github.io/roel/ ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Cross-modal registration on Replica 62](): Cross-modal registration; Replica 62; Rotation Error: 0.217. - [Registration on VECtor (avg)](): Registration; VECtor (avg); Rotational Error: 8.86. - [Registration on VECtor (sofa-fast)](): Registration; VECtor (sofa-fast); Rotational Error (deg): 9.8. - [Panoramic Localization on Replica 62 (room0)](): Panoramic localization; Replica 62 (room0); R Error (°): 5.18. - [Registration on VECtor desk-fast](): Registration; VECtor desk-fast; Rotation Error (°): 10.61. - [Registration on VECtor desk-normal](): Registration; VECtor desk-normal; Rotation Error: 6.75. - [Registration on VECtor (sofa-normal)](): Registration; VECtor (sofa-normal); R Error (deg): 8.3. - [3D Reconstruction on VECtor 65 (average)](): 3D Reconstruction; VECtor 65 (average); Accuracy: 58.46. - [3D Reconstruction on VECtor desk-fast](): 3D Reconstruction; VECtor desk-fast; Accuracy: 42.31. - [3D Reconstruction on VECtor sofa-fast](): 3D Reconstruction; VECtor (sofa-fast); Accuracy: 58.2. - [3D Reconstruction on VECtor desk-normal](): 3D Reconstruction; VECtor desk-normal; Accuracy: 58.2. - [3D Reconstruction on VECtor sofa-normal](): 3D Reconstruction; VECtor (sofa-normal); Accuracy: 75.14. - [3D Reconstruction on Replica](): 3D Reconstruction; Replica; Accuracy: 38.26. ## Original sources and implementation [Original paper]() [PDF]()