AI 中文总结
该研究针对主动三维重建中现有视角选择方法的代理信号与最终目标不一致问题，提出GO-PRE框架，通过最大化预测空间熵降低实现最优视角选择，经实验验证其性能优于现有方法。
AI 中文摘要
主动三维重建依赖主动视角选择，以在有限采集预算下最大化重建保真度。然而，多数现有方法依赖参数不确定性或几何启发式等代理信号，这些信号常与最终目标——渲染预测的保真度——不一致。我们提出GO-PRE，一种面向目标的最优下一个视角选择框架，明确针对预测空间中的信息增益。具体而言，我们将目标表述为最大化用户指定目标视角流形上平均边际预测熵的降低。GO-PRE支持交互式目标指定，并生成高效的获取规则，可实现信息增益的实时计算。跨基准的大量实验表明，GO-PRE相比最先进方法，始终提升主动重建性能并提供更可靠的不确定性量化。
英文摘要
Active 3D reconstruction relies on active view selection to maximize reconstruction fidelity under limited capture budgets. However, most existing methods rely on surrogate signals such as parameter uncertainty or geometric heuristics, but these signals are often misaligned with the ultimate goal: the fidelity of rendered predictions. We propose GO-PRE, a goal-oriented next-best-view selection framework that explicitly targets information gain in the prediction space. Specifically, we formulate the objective as maximizing the reduction of the average marginal predictive entropy over a user-specified target view manifold. GO-PRE supports interactive goal specification and yields an efficient acquisition rule that enables real-time computation of information gain. Extensive experiments across benchmarks demonstrate that GO-PRE consistently improves active reconstruction performance and provides more reliable uncertainty quantification compared to state-of-the-art methods.
CommentsAccepted at the 43rd International Conference on Machine Learning (ICML 2026)
