DRUM: 拡散モデルを用いたレイドロップ対応のSim2Real LiDARセグメンテーションのための非ペア写像
DRUM: Diffusion-based Raydrop-aware Unpaired Mapping for Sim2Real LiDAR Segmentation
シミュレーションで生成したLiDARデータを実データの特性(反射強度とレイドロップノイズ)に合わせて変換する、拡散モデルベースのSim2Real翻訳フレームワークを提案した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Tomoya Miyawaki, Kazuto Nakashima, Yumi Iwashita, Ryo Kurazume
分類: cs.CV, cs.RO
原文アブストラクト
LiDAR-based semantic segmentation is a key component for autonomous mobile robots, yet large-scale annotation of LiDAR point clouds is prohibitively expensive and time-consuming. Although simulators can provide labeled synthetic data, models trained on synthetic data often underperform on real-world data due to a data-level domain gap. To address this issue, we propose DRUM, a novel Sim2Real translation framework. We leverage a diffusion model pre-trained on unlabeled real-world data as a generative prior and translate synthetic data by reproducing two key measurement characteristics: reflectance intensity and raydrop noise. To improve sample fidelity, we introduce a raydrop-aware masked guidance mechanism that selectively enforces consistency with the input synthetic data while preserving realistic raydrop noise induced by the diffusion prior. Experimental results demonstrate that DRUM consistently improves Sim2Real performance across multiple representations of LiDAR data. The project page is available at https://miya-tomoya.github.io/drum.
