PE3R：感知高效的三维重建
PE3R: Perception-Efficient 3D Reconstruction
把 2D 语义先验与多视图几何融合进一个免调优的前馈管线，可直接用于从无位姿图像做开放词表三维语义重建，替代逐场景优化，并可作为三维场景理解中语义与几何联合评测的基线。
原文依据 By integrating multi-view geometry with 2D semantic priors in a feed-forward pipeline, PE3R achieves zero-shot generalization
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期二维到三维感知的进展使得从无位姿图像中恢复三维场景语义成为可能。然而，现有方法往往受限于泛化能力有限、依赖逐场景优化以及跨视角语义不一致等问题。为解决这些局限，我们提出 PE3R，一个免调优框架，用于高效且可泛化的三维语义重建。通过在前馈管线中融合多视图几何与二维语义先验，PE3R 在无需任何场景特定微调的情况下，实现了跨多样场景与物体类别的零样本泛化。在开放词表分割与多视图深度估计上的大量评测表明，PE3R 不仅实现了最高 9 倍的推理加速，还在语义与几何指标上均刷新了最优精度。我们的方法为可扩展、语言驱动的三维场景理解铺平了道路。代码见 github.com/hujiecpp/PE3R。
英文原文摘要 960 字符
Recent advances in 2D-to-3D perception have enabled the recovery of 3D scene semantics from unposed images. However, prevailing methods often suffer from limited generalization, reliance on per-scene optimization, and semantic inconsistencies across viewpoints. To address these limitations, we introduce PE3R, a tuning-free framework for efficient and generalizable 3D semantic reconstruction. By integrating multi-view geometry with 2D semantic priors in a feed-forward pipeline, PE3R achieves zero-shot generalization across diverse scenes and object categories without any scene-specific fine-tuning. Extensive evaluations on open-vocabulary segmentation and multi-view depth estimation show that PE3R not only achieves up to 9xfaster inference but also sets new state-of-the-art accuracy in both semantic and geometric metrics. Our approach paves the way for scalable, language-driven 3D scene understanding. Code is available at github.com/hujiecpp/PE3R.