4DenoiseNet: 隣接点群を用いた悪天候ノイズ除去
4DenoiseNet: Adverse Weather Denoising from Adjacent Point Clouds
LiDAR点群の悪天候ノイズを、時間方向の隣接フレームを活用して除去する深層学習手法を提案し、新規データセットで従来より高精度・高効率を達成した。
著者: Alvari Seppänen, Risto Ojala, Kari Tammi
分類: cs.CV, cs.RO
原文アブストラクト
Reliable point cloud data is essential for perception tasks \textit{e.g.} in robotics and autonomous driving applications. Adverse weather causes a specific type of noise to light detection and ranging (LiDAR) sensor data, which degrades the quality of the point clouds significantly. To address this issue, this letter presents a novel point cloud adverse weather denoising deep learning algorithm (4DenoiseNet). Our algorithm takes advantage of the time dimension unlike deep learning adverse weather denoising methods in the literature. It performs about 10\% better in terms of intersection over union metric compared to the previous work and is more computationally efficient. These results are achieved on our novel SnowyKITTI dataset, which has over 40000 adverse weather annotated point clouds. Moreover, strong qualitative results on the Canadian Adverse Driving Conditions dataset indicate good generalizability to domain shifts and to different sensor intrinsics.
