ImpDet: Exploring Implicit Fields for 3D Object Detection
This work addresses a problem in 3D object detection for autonomous driving by proposing a novel implicit field approach, though it appears incremental as it builds on existing detection paradigms.
The paper tackles the sensitivity of conventional 3D object detection methods to numerical deviations in localization by introducing ImpDet, a framework that views bounding box regression as an implicit function, achieving effectiveness and robustness on KITTI and Waymo benchmarks.
Conventional 3D object detection approaches concentrate on bounding boxes representation learning with several parameters, i.e., localization, dimension, and orientation. Despite its popularity and universality, such a straightforward paradigm is sensitive to slight numerical deviations, especially in localization. By exploiting the property that point clouds are naturally captured on the surface of objects along with accurate location and intensity information, we introduce a new perspective that views bounding box regression as an implicit function. This leads to our proposed framework, termed Implicit Detection or ImpDet, which leverages implicit field learning for 3D object detection. Our ImpDet assigns specific values to points in different local 3D spaces, thereby high-quality boundaries can be generated by classifying points inside or outside the boundary. To solve the problem of sparsity on the object surface, we further present a simple yet efficient virtual sampling strategy to not only fill the empty region, but also learn rich semantic features to help refine the boundaries. Extensive experimental results on KITTI and Waymo benchmarks demonstrate the effectiveness and robustness of unifying implicit fields into object detection.