日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

3D物体検出arXiv:2407.15354

マルチカメラ画像から高解像度ベクトル表現を学習する3D物体検出

Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detection

シェア:XThreadsFacebookLINEはてブBluesky

マルチカメラ画像から高解像度のベクトル表現と低解像度BEV表現を組み合わせ、効率的に3D物体検出を行うVectorFormerを提案。nuScenesで最高精度と高速推論を達成。

著者: Zhili Chen, Shuangjie Xu, Maosheng Ye, Zian Qian, Xiaoyi Zou, Dit-Yan Yeung, Qifeng Chen

分類: cs.CV, cs.RO

原文アブストラクト

The Bird's-Eye-View (BEV) representation is a critical factor that directly impacts the 3D object detection performance, but the traditional BEV grid representation induces quadratic computational cost as the spatial resolution grows. To address this limitation, we present a new camera-based 3D object detector with high-resolution vector representation: VectorFormer. The presented high-resolution vector representation is combined with the lower-resolution BEV representation to efficiently exploit 3D geometry from multi-camera images at a high resolution through our two novel modules: vector scattering and gathering. To this end, the learned vector representation with richer scene contexts can serve as the decoding query for final predictions. We conduct extensive experiments on the nuScenes dataset and demonstrate state-of-the-art performance in NDS and inference time. Furthermore, we investigate query-BEV-based methods incorporated with our proposed vector representation and observe a consistent performance improvement.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI