デジタルツインのためのマテリアル情報を活用したガウシアンスプラッティングによる3D世界再構成
Material-informed Gaussian Splatting for 3D World Reconstruction in a Digital Twin
カメラのみの多視点画像から3Dガウシアンスプラッティングでシーンを再構成し、視覚モデルで素材マスクを抽出して物理ベースのマテリアル特性を割り当てるパイプラインを提案。LiDAR不要でセンサシミュレーションの忠実度を実現。
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: Andy Huynh, João Malheiro Silva, Holger Caesar, Tong Duy Son
分類: cs.CV, cs.RO
原文アブストラクト
3D reconstruction for Digital Twins often relies on LiDAR-based methods, which provide accurate geometry but lack the semantics and textures naturally captured by cameras. Traditional LiDAR-camera fusion approaches require complex calibration and still struggle with certain materials like glass, which are visible in images but poorly represented in point clouds. We propose a camera-only pipeline that reconstructs scenes using 3D Gaussian Splatting from multi-view images, extracts semantic material masks via vision models, converts Gaussian representations to mesh surfaces with projected material labels, and assigns physics-based material properties for accurate sensor simulation in modern graphics engines and simulators. This approach combines photorealistic reconstruction with physics-based material assignment, providing sensor simulation fidelity comparable to LiDAR-camera fusion while eliminating hardware complexity and calibration requirements. We validate our camera-only method using an internal dataset from an instrumented test vehicle, leveraging LiDAR as ground truth for reflectivity validation alongside image similarity metrics.
