新评测框架揭示物体视角规划的真实难点与部署影响
ObjView-Bench: Rethinking Difficulty and Deployment for Object-Centric View Planning
- 拆解视角规划的三类难度：自遮挡、观测饱和难、规划本身复杂度
- 发现预算和可达视角约束会显著改变算法排名与失效模式
- 适合机器人3D重建研究者，尤其关注实际部署性能的团队
物体中心视角规划是机器人主动几何三维重建的核心，但现有评估常将物体复杂度、规划难度、预算假设与物理可达性混为一谈。这导致理想化评估结论难以预测真实重建场景下的表现。本文提出ObjView-Bench，一个重新思考难度与部署的评测框架。首先，分离视角规划评估中的三个核心量：物体自身的全向自遮挡、观测饱和难度，以及基于集合覆盖公式的协议相关规划难度。该分离支持可控数据集构建、慢饱和物体分析，并通过案例研究显示，考虑规划难度的采样可提升学习型视角规划器性能。其次，设计面向部署的评估协议，揭示预算模式与可达视角约束如何改变方法行为。在经典、学习型及混合规划器中，ObjView-Bench表明难度、预算与可达性约束会显著改变算法排名与失败模式。
原文摘要 · Abstract (English)
Object-centric view planning is a core component of active geometric 3D reconstruction in robotics, yet existing evaluations often conflate object complexity, planning difficulty, budget assumptions, and physical reachability constraints. As a result, conclusions drawn from idealized view-planning evaluations may not reliably predict performance under realistic reconstruction settings. We introduce ObjView-Bench, an evaluation framework for rethinking difficulty and deployment in object-centric view planning. First, we disentangle three quantities underlying view-planning evaluation: omnidirectional self-occlusion as an object-side attribute, observation saturation difficulty, and protocol-dependent planning difficulty defined through a set-cover formulation. This separation supports controlled dataset construction, analysis of slow-saturation objects, and a case study showing that planning difficulty-aware sampling can improve learned view planners. Second, we design deployment-oriented evaluation protocols that reveal how budget regimes and reachable-view constraints alter method behavior. Across classical, learned, and hybrid planners, ObjView-Bench shows that difficulty, budget, and reachability constraints substantially change method rankings and failure modes.
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。