基于Transformer的屋顶线框重建边预测
Edge Prediction for Roof Wireframe Reconstruction with Transformers
AI总结：
提出一种端到端Transformer编码器-解码器架构，利用稀疏SfM点云和语义分割图重建3D屋顶线框，在HoHo 22k数据集上取得0.6476的混合结构分数，位列挑战赛第二名。
摘要：
本文提出了一种针对S23DR Challenge 2026的竞争性解决方案，该挑战旨在从稀疏SfM点云、地面级语义分割图和深度图中重建3D房屋屋顶线框模型。我们的方法采用受DETR启发的端到端Transformer编码器-解码器架构。为了有效处理几何和语义数据，稀疏SfM点云输入基于语义优先级进行动态子采样，并增强以Gestalt和ADE20k类别特征。为了进一步增加分割上下文，我们将点特征与额外的Gestalt特征编码融合，这些编码通过将点投影到冻结自编码器产生的潜在特征图中获得。然后，学习到的查询嵌入通过交叉注意力机制直接解码为3D线框边。在“HoHo 22k”数据集上的评估表明，我们的方法显著优于手工和学习的基线方法，取得了0.6476的混合结构分数（HSS），并在挑战赛私有排行榜上获得第二名。
英文摘要：
This paper presents a competitive solution to the S23DR Challenge 2026, which aims to reconstruct 3D house roof wireframe models from sparse SfM point clouds and ground-level semantic segmentations and depth maps. Our proposed method utilizes an end-to-end Transformer encoder-decoder architecture inspired by DETR. To effectively process the geometric and semantic data, the sparse SfM point cloud input is dynamically subsampled based on semantic priority and augmented with Gestalt and ADE20k class features. To further increase segmentation context, we fuse the point features with additional Gestalt feature encodings which are obtained by projecting the points into latent feature maps produced by a frozen autoencoder. Learned query embeddings are then decoded directly into 3D wireframe edges via cross-attention mechanisms. Evaluated on the "HoHo 22k" dataset, our approach significantly outperforms both handcrafted and learned baselines, achieving a Hybrid Structure Score (HSS) of 0.6476 and securing the second-highest position on the challenge's private leaderboard.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
