日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

BEVarXiv:2402.13848

Zero-BEV: 任意の一人称モダリティをBEVマップへゼロショット投影

Zero-BEV: Zero-shot Projection of Any First-Person Modality to BEV Maps

シェア:XThreadsFacebookLINEはてブBluesky

幾何学的な逆透視投影とモダリティ変換を分離することで、学習なしに任意の一人称視点モダリティをBEVマップへ投影する手法を提案。

著者: Gianluca Monaci, Leonid Antsfeld, Boris Chidlovskii, Christian Wolf

分類: cs.CV, cs.RO

原文アブストラクト

Bird's-eye view (BEV) maps are an important geometrically structured representation widely used in robotics, in particular self-driving vehicles and terrestrial robots. Existing algorithms either require depth information for the geometric projection, which is not always reliably available, or are trained end-to-end in a fully supervised way to map visual first-person observations to BEV representation, and are therefore restricted to the output modality they have been trained for. In contrast, we propose a new model capable of performing zero-shot projections of any modality available in a first person view to the corresponding BEV map. This is achieved by disentangling the geometric inverse perspective projection from the modality transformation, eg. RGB to occupancy. The method is general and we showcase experiments projecting to BEV three different modalities: semantic segmentation, motion vectors and object bounding boxes detected in first person. We experimentally show that the model outperforms competing methods, in particular the widely used baseline resorting to monocular depth estimation.

  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

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI