[论文] [论文] φ-RIE: From Photorealistic Reconstruction to Interactive Env...

论文概要

研究领域: CV
作者: Runyi Yang, Deheng Zhang, Xiaoye Wang, Kanzhi Wu, Lei Sun et al.
发布时间: 2026-09-22
arXiv: 2609.26795

中文摘要

3D 高斯泼溅（3DGS）能以照片级真实感重建所摄场景，但所得表示本身并不支持物理交互；机器人仿真却要求对象级变化——对象须独立移动、相互接触，并揭示先前被遮挡的环境。差距源于对象外观可能与背景纠缠，且隐藏的对象几何与被遮挡背景可能从未被观测。为此我们提出 φ-RIE：一条高斯原生流水线，将选定对象转换为可移动的仿真器资产，同时保留其余重建。关键观察是资产构建与源场景移除应当耦合——同一对象身份既定义可移动资产，也定义需移除并补全的场景内容。据此，场景观测为"耦合场景构建"提供共享证据，产出已配准资产与补全后的背景高斯，供仿真器驱动的交互环境渲染。耦合在保持视觉与物理状态一致的同时保留未编辑高斯。在 50 个 ScanNet++ 场景上，基于证据的选择与配准重试在固定保留率下将 20mm 匹配 F1 从 0.336 提至 0.383。更多测试证明资产可执行性、相对单生成器基线的操控增益，以及转换的视觉代价。这些结果共同表明 φ-RIE 实现了交互式场景转换。

原文摘要

3D Gaussian Splatting (3DGS) can reconstruct a captured scene photorealistically, but the resulting representation does not by itself support physical interaction. Robot simulation instead requires object-level change, \textit{i.e.}, objects must move independently, make contact, and reveal previously occluded surroundings. This gap arises because object appearance may remain entangled with the background, while hidden object geometry and occluded background content may be unobserved. To address this challenge, we present φ-RIE, a Gaussian-native pipeline that converts selected objects into movable simulator assets while preserving the remaining reconstruction. Our key observation is that asset construction and source removal should be coupled, \textit{i.e.}, one object identity should define the movable asset and the scene content to remove and complete. Accordingly, Scene Observation supplies shared evidence to Coupled Scene Construction, which creates registered assets and completed background Gaussians for simulator-driven rendering in an Interactive Environment. This coupling preserves unedited Gaussians while aligning visual and physical state. On 50 ScanNet++ scenes, evidence-based selection and registration retry increase matched F1 at 20,mm from 0.336 to 0.383 at fixed retention. Further tests demonstrate asset executability, manipulation gains over a single-generator baseline, and the visual cost of conversion. Together, these results demonstrate that \name\ enables interactive scene conversion.

自动采集于 2026-09-24

#论文 #arXiv #CV #小凯