通过平面约束与不确定性采样，提升机器人环境3D占据预测的精度与细节。
EmbodiedOcc++: Boosting Embodied 3D Occupancy Prediction with Plane Regularization and Uncertainty Sampler
- 用平面正则化约束高斯点位置，使其贴合墙面等平面结构。
- 在连续帧重叠区域自适应选择更新点，减少误判。
- 兼顾几何精度与计算效率，适合实时机器人感知场景。
在线3D占据预测为具身环境提供全面的空间理解。尽管创新的EmbodiedOcc框架利用3D语义高斯点实现渐进式室内占据预测，但忽略了室内环境以平面结构为主的几何特征。本文提出EmbodiedOcc++，引入两项关键改进：几何引导精修模块（GRM）通过平面正则化约束高斯点更新，以及语义感知不确定性采样器（SUS）在连续帧重叠区域更有效地选择更新对象。GRM根据曲率与深度约束自适应调整正则化权重，使语义高斯点准确对齐平面表面，同时在复杂区域保持灵活性。SUS自适应选择需更新的高斯点，增强多视角间几何一致性。在EmbodiedOcc-ScanNet基准上的全面实验表明，EmbodiedOcc++在不同设置下均达到当前最优性能，显著提升边缘精度并保留更多几何细节，同时保证计算效率，这对在线具身感知至关重要。代码将发布于：https://github.com/PKUHaoWang/EmbodiedOcc2。
原文摘要 · Abstract (English)
Online 3D occupancy prediction provides a comprehensive spatial understanding of embodied environments. While the innovative EmbodiedOcc framework utilizes 3D semantic Gaussians for progressive indoor occupancy prediction, it overlooks the geometric characteristics of indoor environments, which are primarily characterized by planar structures. This paper introduces EmbodiedOcc++, enhancing the original framework with two key innovations: a Geometry-guided Refinement Module (GRM) that constrains Gaussian updates through plane regularization, along with a Semantic-aware Uncertainty Sampler (SUS) that enables more effective updates in overlapping regions between consecutive frames. GRM regularizes the position update to align with surface normals. It determines the adaptive regularization weight using curvature-based and depth-based constraints, allowing semantic Gaussians to align accurately with planar surfaces while adapting in complex regions. To effectively improve geometric consistency from different views, SUS adaptively selects proper Gaussians to update. Comprehensive experiments on the EmbodiedOcc-ScanNet benchmark demonstrate that EmbodiedOcc++ achieves state-of-the-art performance across different settings. Our method demonstrates improved edge accuracy and retains more geometric details while ensuring computational efficiency, which is essential for online embodied perception. The code will be released at: https://github.com/PKUHaoWang/EmbodiedOcc2.
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。