用流匹配扩散模型重建稀疏3D线框，精度达0.654。
S23DR 2026 Winning Solution
- 将顶点视为条件集合，用流匹配DiT去噪64个顶点令牌
- 分两阶段优化：全局粗结构+壳裁剪精修，提升几何一致性
- 多采样共识机制稳定随机采样，适合3D重建任务
本文提出S23DR 2026挑战赛中结构化3D线框重建的优胜方案，基于稀疏SfM、拟合深度图和语义分割进行重建。方法将顶点建模为条件集合，利用基于Perceiver风格场景令牌的流匹配扩散变换器（DiT）对64个顶点令牌进行去噪。系统采用双阶段流程：第一阶段全局预测粗略结构，第二阶段通过壳裁剪进行精细化修正；最后加入小规模多采样共识步骤，确保随机采样过程稳定。最终系统在私有排行榜上排名第一，达到HSS = 0.654。
原文摘要 · Abstract (English)
This text presents the winning solution to the S23DR 2026 challenge for structured 3D wireframe reconstruction from sparse SfM, fitted depth, and semantic segmentations. The method treats vertices as a conditional set and denoises 64 vertex tokens with a flow-matching DiT conditioned on Perceiver-style scene tokens. A global pass predicts the coarse structure, a hull-cropped second pass refines it, and a small multi-sample consensus step keeps the stochastic sampler well behaved. The final system ranked first on the private leaderboard, achievingHSS = 0.654.
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。