RadarSFD: 事前学習済み事前分布を用いた単一フレーム拡散によるレーダ点群生成
RadarSFD: Single-Frame Diffusion with Pretrained Priors for Radar Point Clouds
単一のミリ波レーダフレームから、事前学習済み単眼深度推定器の幾何学的知識を活用した条件付き潜在拡散モデルにより、LiDARのような高密度点群を再構成する手法を提案。
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: Bin Zhao, Nakul Garg
分類: cs.RO, eess.SP
原文アブストラクト
Millimeter-wave radar provides robust perception in fog, smoke, dust, and low light, making it attractive for size-, weight-, and power-constrained robotic platforms. Existing radar imaging methods typically rely on synthetic aperture or multi-frame aggregation to improve resolution, which is impractical for small aerial, inspection, or wearable systems. We present RadarSFD, a conditional latent diffusion framework that reconstructs dense LiDAR-like point clouds from a single radar frame without motion or SAR. Our approach transfers geometric priors from a pretrained monocular depth estimator into the diffusion backbone, anchors them to radar inputs via channel-wise latent concatenation, and regularizes outputs with a dual-space objective combining latent and pixel-space losses. On the RadarHD benchmark, RadarSFD achieves state-of-the-art performance against baseline models. Qualitative results show recovery of fine walls and narrow gaps, and experiments across new environments confirm strong generalization. Ablation studies highlight the importance of pretrained initialization, radar BEV conditioning, and the dual-space loss. Together, these results establish a practical single-frame, no-SAR mmWave radar pipeline for dense point cloud perception in compact robotic systems.
関連論文
- レンジ画像で駆動する拡散モデルによるミリ波レーダー点群の高密度化点群生成/拡散モデル
