用角点替代中心点做3D目标检测，提升稀疏区域预测稳定性。
Rethinking the Encoding and Annotating of 3D Bounding Box: Corner-Aware 3D Object Detection from Point Clouds
- 将检测目标从不稳定的中心改为密集区域的角点
- 仅需鸟瞰图角点点击即可达到全监督83%精度
- 可无缝接入现有检测器，适合点云数据稀疏场景
基于激光雷达的3D目标检测主流采用中心对齐回归，但因点云前表面偏倚，物体中心常位于鸟瞰图中稀疏或空旷区域，导致边界框预测噪声大、不准确。为克服此问题，本文重新思考边界框表示方式，提出角点对齐回归：将预测目标从不稳定中心转向几何信息丰富的角点，这些角点位于密集可观测区域。利用角点间的固有几何约束及2D图像框关系，仅需角点标注即可恢复部分3D框参数，实现弱监督训练。设计了一个简单有效的角点感知检测头，可直接嵌入现有检测器。KITTI实验表明，该方法相比中心基线提升3.5% AP，仅用鸟瞰图角点点击即达全监督83%准确率，验证了角点对齐回归的有效性。
原文摘要 · Abstract (English)
Center-aligned regression remains dominant in LiDAR-based 3D object detection, yet it suffers from fundamental instability: object centers often fall in sparse or empty regions of the bird's-eye-view (BEV) due to the front-surface-biased nature of LiDAR point clouds, leading to noisy and inaccurate bounding box predictions. To circumvent this limitation, we revisit bounding box representation and propose corner-aligned regression, which shifts the prediction target from unstable centers to geometrically informative corners that reside in dense, observable regions. Leveraging the inherent geometric constraints among corners and image 2D boxes, partial parameters of 3D bounding boxes can be recovered from corner annotations, enabling a weakly supervised paradigm without requiring complete 3D labels. We design a simple yet effective corner-aware detection head that can be plugged into existing detectors. Experiments on KITTI show our method improves performance by 3.5% AP over center-based baseline, and achieves 83% of fully supervised accuracy using only BEV corner clicks, demonstrating the effectiveness of our corner-aware regression strategy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。