ImpDet: Exploring Implicit Fields for 3D Object Detection

TL;DR

ImpDet introduces a novel 3D object detection framework that models bounding boxes as implicit fields, leveraging surface point information and virtual sampling to improve boundary accuracy and robustness.

Contribution

The paper proposes ImpDet, a new implicit field-based approach for 3D detection that enhances boundary quality and robustness over traditional bounding box regression methods.

Findings

Outperforms existing methods on KITTI and Waymo benchmarks.

Effectively handles boundary ambiguity with implicit field learning.

Improves detection robustness through virtual sampling strategy.

Abstract

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.