用单目图像实现高精度语义三维重建，提升几何与语义一致性。
MOSE: Monocular Semantic Reconstruction Using NeRF-Lifted Noisy Priors
- 利用通用无类别的分割掩码引导语义渲染的一致性
- 在无纹理区域施加平滑正则化，改善几何质量
- 适用于需要高质量3D语义建模的场景理解任务
从单目图像中准确重建稠密且语义标注的三维网格仍具挑战，主要源于缺乏几何引导和视图依赖的二维先验不完善。尽管隐式神经场景表示已能在多视角图像下实现精确的二维渲染，但仅使用单目先验的三维场景理解研究仍较少。本文提出MOSE，一种基于神经场的语义重建方法，将推断出的图像级噪声先验提升至三维空间，实现在三维与二维空间中均具备准确的语义与几何。核心思想是利用通用的无类别分割掩码作为指导，促进训练过程中语义渲染的局部一致性。借助语义信息，进一步对无纹理区域施加平滑正则化，从而实现几何与语义的相互增益。在ScanNet数据集上的实验表明，MOSE在3D语义分割、2D语义分割和3D表面重建任务中均优于现有基线方法。
原文摘要 · Abstract (English)
Accurately reconstructing dense and semantically annotated 3D meshes from monocular images remains a challenging task due to the lack of geometry guidance and imperfect view-dependent 2D priors. Though we have witnessed recent advancements in implicit neural scene representations enabling precise 2D rendering simply from multi-view images, there have been few works addressing 3D scene understanding with monocular priors alone. In this paper, we propose MOSE, a neural field semantic reconstruction approach to lift inferred image-level noisy priors to 3D, producing accurate semantics and geometry in both 3D and 2D space. The key motivation for our method is to leverage generic class-agnostic segment masks as guidance to promote local consistency of rendered semantics during training. With the help of semantics, we further apply a smoothness regularization to texture-less regions for better geometric quality, thus achieving mutual benefits of geometry and semantics. Experiments on the ScanNet dataset show that our MOSE outperforms relevant baselines across all metrics on tasks of 3D semantic segmentation, 2D semantic segmentation and 3D surface reconstruction.
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。