发表机构
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对3DGS多尺度分割中几何与语义脱节及掩码监督不完整的问题，提出PePESeg3D，将感知先验注入几何重建与对比学习，在多个基准上实现最先进的分割与重建性能。
AI 中文摘要
近年来，3D高斯溅射（3DGS）的进展已将其能力扩展到多尺度分割。现有方法使用高斯原语重建场景，并分别学习多尺度分割特征，这使得几何结构对语义结构不敏感，且特征学习依赖于不完整的掩码监督。为解决这些局限性，我们提出了PePESeg3D，一种将感知先验注入多尺度3D高斯分割流水线的新框架。为充分利用感知先验，我们不仅将其整合到对比特征学习中，还整合到上游几何重建中。具体而言，PePE重建利用单目深度和掩码约束以确保语义连贯的对象结构。基于这种对齐的几何，PePE对比学习利用密集深度-颜色线索和视图一致的质心监督，以弥补从2D基础模型获得的多尺度掩码的不完整性。在SPIn-NeRF、LERF-Mask和NVOS基准上的广泛实验表明，PePESeg3D在多尺度分割和场景重建方面均达到了最先进的性能，突显了将感知先验整合到几何优化和特征学习中对准确的多尺度3D分割的重要性。我们的代码可在该https URL获取。
英文摘要
Recent advancements in 3D Gaussian Splatting (3DGS) have extended its capabilities to multi-scale segmentation. Existing methods reconstruct a scene with Gaussian primitives and learn multi-scale segmentation features separately, which leaves the geometry unaware of semantic structure and the feature learning dependent on incomplete mask supervision. To address these limitations, we present PePESeg3D, a novel framework that injects perception priors into a multi-scale 3D Gaussian segmentation pipeline. To fully exploit perception priors, we integrate them not only into contrastive feature learning but also into the upstream geometry reconstruction. Specifically, PePE Reconstruction incorporates monocular depth and mask constraints to ensure semantically coherent object structures. Building on this aligned geometry, PePE Contrastive Learning leverages dense depth-color cues and view-consistent centroid supervision to compensate for the incompleteness of multi-scale masks obtained from a 2D foundation model. Extensive experiments on the SPIn-NeRF, LERF-Mask, and NVOS benchmarks demonstrate that PePESeg3D achieves state-of-the-art performance in both multi-scale segmentation and scene reconstruction, highlighting the importance of integrating perception priors into both geometry optimization and feature learning for accurate multi-scale 3D segmentation. Our code is available at https://github.com/BeCow5X5/PePESeg3D.
CommentsAccepted to BMVC 2026
