FRA-NBV: A Fast and Reflectivity-Aware Next-Best-View Strategy
2026-08-03 • Robotics
Robotics
AI summaryⓘ
The authors address the problem of using depth sensors to create 3D models of shiny, reflective objects, which often cause missing or bad data. They developed a method called FRA-NBV that finds these tricky reflective spots by spotting where data is missing and then changes the sensor's angle to get better measurements. This method works without needing prior knowledge about the object's shape or material, making it practical for many industrial uses. Their tests show that their approach helps create more complete 3D reconstructions even with low-cost sensors and challenging shiny surfaces.
3D reconstructiondepth sensorsnext-best-view (NBV)reflective surfacesdepth losssensor angle of incidenceellipsoid representationindustrial inspectionlow-resolution depth sensing
Authors
G. F. Preziosa, E. Setti, M. Faroni, A. M. Zanchettin, P. Rocco
Abstract
Autonomous 3D reconstruction with depth sensors is strongly affected by reflective surfaces, which cause missing or unreliable measurements and reduce the effectiveness of conventional Next-Best-View (NBV) strategies. This limitation is particularly critical in industrial applications involving reflective components and low-cost, low-resolution depth sensing, where robustness to sensing failures is essential. This paper proposes a Fast Reflectivity-Aware Next-Best-View (FRA-NBV) strategy that explicitly addresses reflection-induced depth loss without relying on prior object models or assumptions on material reflectance, making it suitable for a wide range of industrial configurations. Reflective regions are identified from the spatial distribution of missing depth measurements and localized in three-dimensional space using an online ellipsoid-based representation of the object estimate. A recovery strategy then selects additional poses that modify the sensor's angle of incidence to improve the likelihood of reconstructing the affected regions. Experiments on objects with different geometric and reflective complexity demonstrate that the approach significantly improves reconstruction coverage under realistic industrial conditions.