日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

sim2realarXiv:2210.12682

フォトリアリスティック神経ドメインランダム化

Photo-realistic Neural Domain Randomization

シェア:XThreadsFacebookLINEはてブBluesky

ニューラルレンダリングを活用し、物理ベースのレイトレーシングを模倣するニューラルネットワーク群を学習することで、オンラインでフォトリアルな画像拡張を生成し、sim-to-realギャップを埋める手法を提案。

著者: Sergey Zakharov, Rares Ambrus, Vitor Guizilini, Wadim Kehl, Adrien Gaidon

分類: cs.CV, cs.RO

原文アブストラクト

Synthetic data is a scalable alternative to manual supervision, but it requires overcoming the sim-to-real domain gap. This discrepancy between virtual and real worlds is addressed by two seemingly opposed approaches: improving the realism of simulation or foregoing realism entirely via domain randomization. In this paper, we show that the recent progress in neural rendering enables a new unified approach we call Photo-realistic Neural Domain Randomization (PNDR). We propose to learn a composition of neural networks that acts as a physics-based ray tracer generating high-quality renderings from scene geometry alone. Our approach is modular, composed of different neural networks for materials, lighting, and rendering, thus enabling randomization of different key image generation components in a differentiable pipeline. Once trained, our method can be combined with other methods and used to generate photo-realistic image augmentations online and significantly more efficiently than via traditional ray-tracing. We demonstrate the usefulness of PNDR through two downstream tasks: 6D object detection and monocular depth estimation. Our experiments show that training with PNDR enables generalization to novel scenes and significantly outperforms the state of the art in terms of real-world transfer.

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

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