日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

深度推定arXiv:2301.06715

SwinDepth: Swin Transformerと密結合カスケードネットワークによる単眼シーケンスからの教師なし深度推定

SwinDepth: Unsupervised Depth Estimation using Monocular Sequences via Swin Transformer and Densely Cascaded Network

シェア:XThreadsFacebookLINEはてブBluesky

畳み込みを使わないSwin Transformerを特徴抽出器に採用し、異なるスケールの特徴マップを密に結合するDCMNetを提案することで、単眼動画からの教師なし深度推定精度を向上させた研究。

著者: Dongseok Shim, H. Jin Kim

分類: cs.CV, cs.LG, cs.RO

原文アブストラクト

Monocular depth estimation plays a critical role in various computer vision and robotics applications such as localization, mapping, and 3D object detection. Recently, learning-based algorithms achieve huge success in depth estimation by training models with a large amount of data in a supervised manner. However, it is challenging to acquire dense ground truth depth labels for supervised training, and the unsupervised depth estimation using monocular sequences emerges as a promising alternative. Unfortunately, most studies on unsupervised depth estimation explore loss functions or occlusion masks, and there is little change in model architecture in that ConvNet-based encoder-decoder structure becomes a de-facto standard for depth estimation. In this paper, we employ a convolution-free Swin Transformer as an image feature extractor so that the network can capture both local geometric features and global semantic features for depth estimation. Also, we propose a Densely Cascaded Multi-scale Network (DCMNet) that connects every feature map directly with another from different scales via a top-down cascade pathway. This densely cascaded connectivity reinforces the interconnection between decoding layers and produces high-quality multi-scale depth outputs. The experiments on two different datasets, KITTI and Make3D, demonstrate that our proposed method outperforms existing state-of-the-art unsupervised algorithms.

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