DETR3D: 3D-to-2Dクエリによるマルチビュー画像からの3D物体検出
DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries
複数カメラ画像から2D特徴を抽出し、3D物体クエリで2D特徴を参照して直接3D空間でバウンディングボックスを予測するマルチカメラ3D物体検出手法を提案。nuScenesで最先端性能を達成。
著者: Yue Wang, Vitor Guizilini, Tianyuan Zhang, Yilun Wang, Hang Zhao, Justin Solomon
分類: cs.CV, cs.AI, cs.LG, cs.RO
原文アブストラクト
We introduce a framework for multi-camera 3D object detection. In contrast to existing works, which estimate 3D bounding boxes directly from monocular images or use depth prediction networks to generate input for 3D object detection from 2D information, our method manipulates predictions directly in 3D space. Our architecture extracts 2D features from multiple camera images and then uses a sparse set of 3D object queries to index into these 2D features, linking 3D positions to multi-view images using camera transformation matrices. Finally, our model makes a bounding box prediction per object query, using a set-to-set loss to measure the discrepancy between the ground-truth and the prediction. This top-down approach outperforms its bottom-up counterpart in which object bounding box prediction follows per-pixel depth estimation, since it does not suffer from the compounding error introduced by a depth prediction model. Moreover, our method does not require post-processing such as non-maximum suppression, dramatically improving inference speed. We achieve state-of-the-art performance on the nuScenes autonomous driving benchmark.
