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検出arXiv:2301.13592

事前情報は強力:2D事前情報でマルチカメラ3D検出のTransformerを改善

Priors are Powerful: Improving a Transformer for Multi-camera 3D Detection with 2D Priors

シェア:XThreadsFacebookLINEはてブBluesky

2D画像認識モデルの予測を事前情報として活用し、マルチカメラ3D物体検出のTransformerのクエリ初期化や特徴量を改善することで、精度を最大12%向上させた。

著者: Di Feng, Francesco Ferroni

分類: cs.CV, cs.RO

原文アブストラクト

Transfomer-based approaches advance the recent development of multi-camera 3D detection both in academia and industry. In a vanilla transformer architecture, queries are randomly initialised and optimised for the whole dataset, without considering the differences among input frames. In this work, we propose to leverage the predictions from an image backbone, which is often highly optimised for 2D tasks, as priors to the transformer part of a 3D detection network. The method works by (1). augmenting image feature maps with 2D priors, (2). sampling query locations via ray-casting along 2D box centroids, as well as (3). initialising query features with object-level image features. Experimental results shows that 2D priors not only help the model converge faster, but also largely improve the baseline approach by up to 12% in terms of average precision.

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. 2GXO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
  3. 3newmo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
  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

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI