Rewis3d：三维重建提升弱监督语义分割
Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentation
把前馈三维重建得到的点云作为辅助监督信号，通过双师生架构在2D图像与重建3D点云之间施加语义一致性，从而把稀疏标注传播到整个场景；做稀疏标注分割或想利用视频几何线索补监督的人可直接复用这一思路。
原文依据 a dual student-teacher architecture enforces semantic consistency between 2D images and reconstructed 3D point clouds
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 Rewis3d，一个利用近期前馈三维重建进展来显著提升二维图像弱监督语义分割的框架。获取稠密像素级标注仍是训练分割模型的昂贵瓶颈。稀疏标注为此提供了一种高效的弱监督替代方案，但仍存在性能差距。为解决这一问题，我们引入一种新方法，利用三维场景重建作为辅助监督信号。我们的关键洞见是：从二维视频中恢复的三维几何结构提供了强有力线索，可将稀疏标注传播到整个场景。具体而言，双师生架构在二维图像与重建的三维点云之间施加语义一致性，并利用最优的前馈重建生成可靠的几何监督。大量实验表明，Rewis3d 在稀疏监督下达到最优性能，在无需额外标注或推理开销的情况下比现有方法高出 2-7%。项目主页：https://rewis3d-mpi.github.io/Rewis3d/
英文原文摘要 1181 字符
We present Rewis3d, a framework that leverages recent advances in feed-forward 3D reconstruction to significantly improve weakly supervised semantic segmentation on 2D images. Obtaining dense, pixel-level annotations remains a costly bottleneck for training segmentation models. Alleviating this issue, sparse annotations offer an efficient weakly-supervised alternative. However, they still incur a performance gap. To address this, we introduce a novel approach that leverages 3D scene reconstruction as an auxiliary supervisory signal. Our key insight is that 3D geometric structure recovered from 2D videos provides strong cues that can propagate sparse annotations across entire scenes. Specifically, a dual student-teacher architecture enforces semantic consistency between 2D images and reconstructed 3D point clouds, using state-of-the-art feed-forward reconstruction to generate reliable geometric supervision. Extensive experiments demonstrate that Rewis3d achieves state-of-the-art performance in sparse supervision, outperforming existing approaches by 2-7% without requiring additional labels or inference overhead. Project page: https://rewis3d-mpi.github.io/Rewis3d/