边缘争夺信任：面向点云建筑重建的组相对边缘优化
Edges Compete for Trust: Group Relative Edge Optimization for Building Reconstruction from Point Clouds
把一对一边匹配的稀疏监督换成基于几何对齐质量的组内相对奖励，再转成置信度分布做交叉熵监督，这个思路可直接迁移到任何「候选提案多、标注少」的检测/线框/关键点任务上，且不增加推理开销。
原文依据 computes edge-level rewards based on geometric alignment quality and transforms them into target confidence distributions via group-wise normalization
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论建筑重建旨在从点云中提取紧凑的线框。近期基于边缘的方法取得了令人瞩目的结果，但受困于一对一匹配带来的稀疏监督，导致大多数边缘提案未被充分优化。本文提出组相对边缘优化（GREO），首次尝试在线框重建中通过强化学习式优化，激励对边缘提案的稠密监督。具体而言，GREO 基于几何对齐质量计算边缘级奖励，并通过组内归一化将其转换为目标置信度分布。此外，我们引入熵正则化以维持分布稳定性并防止置信度坍缩。这种联合优化通过交叉熵最小化，实现了对所有边缘提案的稠密且具有判别性的监督。在大规模 Building3D 数据集上的实验表明，我们强大且通用的 GREO 可作为即插即用的训练策略无缝集成到现有基于边缘的方法中，在 Entry-level 和 Tallinn 两个基准上均达到最优性能，且不增加推理开销。
英文原文摘要 1198 字符
Building reconstruction aims to extract compact wireframes from point clouds. Recent edge-based methods achieve impressive results but suffer from sparse supervision from one-to-one matching, which leaves most edge proposals under-optimized. In this paper, we present Group Relative Edge Optimization (GREO), the first attempt to incentivize dense supervision across edges proposals through reinforcement learning-style optimization in wireframe reconstruction. Specifically, GREO computes edge-level rewards based on geometric alignment quality and transforms them into target confidence distributions via group-wise normalization. In addition, we incorporate entropy regularization to maintain distributional stability and prevent confidence collapse. This joint optimization enables dense and discriminative supervision across all edge proposals through cross-entropy minimization. Experiments on the large-scale Building3D dataset demonstrate that our powerful and versatile GREO integrates seamlessly into existing edge-based methods as a plug-and-play training strategy, achieving state-of-the-art performance on both the Entry-level and Tallinn benchmarks while adding no inference overhead.