# Revisiting 3D Object Detection From an Egocentric Perspective Source: [Revisiting 3D Object Detection From an Egocentric Perspective]() Collection index: [llms.txt]() Data updated: 2026-01-01T14:03:02.857Z Authors: Boyang Deng, Charles R. Qi, Mahyar Najibi, Thomas Funkhouser, Yin Zhou, Dragomir Anguelov Published: 2021-12-14T23:24:25.000Z ## Abstract 3D object detection is a key module for safety-critical robotics applications such as autonomous driving. For these applications, we care most about how the detections affect the ego-agent's behavior and safety (the egocentric perspective). Intuitively, we seek more accurate descriptions of object geometry when it's more likely to interfere with the ego-agent's motion trajectory. However, current detection metrics, based on box Intersection-over-Union (IoU), are object-centric and aren't designed to capture the spatio-temporal relationship between objects and the ego-agent. To address this issue, we propose a new egocentric measure to evaluate 3D object detection, namely Support Distance Error (SDE). Our analysis based on SDE reveals that the egocentric detection quality is bounded by the coarse geometry of the bounding boxes. Given the insight that SDE would benefit from more accurate geometry descriptions, we propose to represent objects as amodal contours, specifically amodal star-shaped polygons, and devise a simple model, StarPoly, to predict such contours. Our experiments on the large-scale Waymo Open Dataset show that SDE better reflects the impact of detection quality on the ego-agent's safety compared to IoU; and the estimated contours from StarPoly consistently improve the egocentric detection quality over recent 3D object detectors. ## 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. - [3D Object Detection on Waymo Open Dataset](): 3D Object Detection; Waymo Open Dataset; SDE-APD: not recorded. - [3D Object Detection on Waymo Open Dataset (SDE-APD, IoU-APD, IoU-AP)](): 3D Object Detection; Waymo Open Dataset; SDE-APD: not recorded. ## Original sources and implementation [Original paper]() [PDF]()