关于自回归3D目标检测的可行性与机会
On the Feasibility and Opportunity of Autoregressive 3D Object Detection
AI总结：
AutoReg3D通过自回归序列生成方法实现3D目标检测，无需锚点或NMS，展示了在LiDAR检测中的可行性与灵活性。
摘要：
基于LiDAR的3D目标检测器通常依赖于带有手工设计组件的建议头，如锚点分配和非极大值抑制（NMS），这使训练变得复杂并限制了扩展性。我们提出了AutoReg3D，一种自回归3D检测器，将检测视为序列生成。在点云特征给定的情况下，AutoReg3D以范围因果（由近到远）的顺序发射对象，并将每个对象编码为由其中心、大小、方向、速度和类别的短离散令牌序列组成。这种由近到远的顺序反映了LiDAR几何结构——近处的对象会遮挡远处的对象，但不会反之。这使得在训练期间可以实现简单的教师强制，并在测试时实现自回归解码。AutoReg3D能够在多样化的点云或骨干网络上兼容，并且在不使用锚点或NMS的情况下达到具有竞争力的nuScenes性能。除了达到平局外，序列化形式解锁了语言模型的进步，包括用于任务对齐目标的GRPO式强化学习。这些结果将自回归解码定位为一种可行且灵活的LiDAR基于检测的替代方案，并为将现代序列建模工具引入3D感知开辟了道路。
英文摘要：
LiDAR-based 3D object detectors typically rely on proposal heads with hand-crafted components like anchor assignment and non-maximum suppression (NMS), complicating training and limiting extensibility. We present AutoReg3D, an autoregressive 3D detector that casts detection as sequence generation. Given point-cloud features, AutoReg3D emits objects in a range-causal (near-to-far) order and encodes each object as a short, discrete-token sequence consisting of its center, size, orientation, velocity, and class. This near-to-far ordering mirrors LiDAR geometry--near objects occlude far ones but not vice versa--enabling straightforward teacher forcing during training and autoregressive decoding at test time. AutoReg3D is compatible across diverse point-cloud or backbones and attains competitive nuScenes performance without anchors or NMS. Beyond parity, the sequential formulation unlocks language-model advances for 3D perception, including GRPO-style reinforcement learning for task-aligned objectives. These results position autoregressive decoding as a viable, flexible alternative for LiDAR-based detection and open a path to importing modern sequence-modeling tools into 3D perception.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
