单图推断被遮挡的多层几何结构，一次前传完成完整重建。
LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning
- 用分层点图预测相机射线穿过的多层表面。
- 在五个数据集上实现端到端完整重建，无需迭代优化。
- 适合需要精准几何推理的物体与场景重建任务。
我们提出分层射线相交（LaRI），一种完全监督的单图像遮挡几何推理方法。与传统深度估计仅限可见表面不同，LaRI利用分层点图预测相机射线穿过的多个表面。相比依赖神经隐式表示或迭代优化的现有方法，LaRI可在一次前向传播中完成完整场景重建，支持高效且视图对齐的几何推理，适用于物体级与场景级任务。我们进一步提出预测射线停止索引，以识别LaRI输出中有效的相交像素与层级。为更好支撑和评估该任务，我们使用渲染引擎构建标注流程，在五个公开数据集（含合成与真实数据）上生成标注，覆盖3D物体与场景。作为通用方法，LaRI在物体级与场景级重建任务中均得到验证。
原文摘要 · Abstract (English)
We present Layered Ray Intersections (LaRI), a fully supervised method for occluded geometry reasoning from a single image. Unlike conventional depth estimation, which is limited to visible surfaces, LaRI predicts multiple surfaces intersected by the camera rays using layered point maps. Compared to the existing approaches that leverage neural implicit representations or iterative refinement, LaRI achieves complete scene reconstruction in one feed-forward pass, enabling efficient and view-aligned geometric reasoning to underpin both object-level and scene-level tasks. We further propose to predict the ray stopping index, which identifies valid intersecting pixels and layers from LaRI's output. To better underpin and evaluate this task, we build an annotation pipeline using rendering engines, construct annotations for five public datasets, including synthetic and real-world data covering 3D objects and scenes. As a generic method, LaRI's performance is validated in object-level and scene-level reconstruction tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。