RayLift: 3D幾何学事前知識を用いた相補的なレイ単位証拠のリフティングによるセマンティックシーン補完
RayLift: Lifting Complementary Ray-Wise Evidence with 3D Geometry Priors for Semantic Scene Completion
カメラベースの3Dセマンティックシーン補完において、ステレオ深度の不確実性を考慮し、レイ単位の証拠を適応的にサンプリング・重み付けすることで、高精度な3D構造復元を実現する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: Meng Wang, Hongxia Yu, Wenzhe He, Xingdong Song, Huilong Pi, Jiapeng Zhang, Ruihui Li
分類: cs.CV
原文アブストラクト
Camera-based 3D semantic scene completion (SSC) provides comprehensive scene understanding for autonomous driving and robotics. However, existing methods often treat stereo depth estimates as deterministic geometric constraints, causing depth uncertainty and local correspondence errors to propagate directly into voxel representations. To address this issue, we propose RayLift, a framework that uses stereo geometry as a metric reference while incorporating complementary ray evidence to recover reliable 3D structures adaptively. RayLift first employs a Complementary Context Encoder that extracts geometry-aware priors from a frozen 3D vision foundation model, thereby enriching the scene context. It then introduces a Depth Ray Evidence Lifter module that jointly models geometric dissimilarity, depth confidence, and spatial uncertainty to adaptively sample and weight candidate surface locations along each camera ray. Finally, a Semantic-Aware Voxel Integrator injects the resulting ray evidence into voxel features by explicitly modeling their spatial support. Extensive experiments on SemanticKITTI and SSCBench-KITTI-360 demonstrate that RayLift achieves competitive performance and consistently outperforms existing methods.