Explorerโ€บComputer Visionโ€บComputer Vision
Research PaperResearchia:202609.23005

ฯ†-RIE: From Photorealistic Reconstruction to Interactive Environments

Runyi Yang

Abstract

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...

Submitted: September 23, 2026Subjects: Computer Vision; Computer Vision

Description / Details

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 ฯ†-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.


Source: arXiv:2609.26795v1 - http://arxiv.org/abs/2609.26795v1 PDF: https://arxiv.org/pdf/2609.26795v1 Original Link: http://arxiv.org/abs/2609.26795v1

Please sign in to join the discussion.

No comments yet. Be the first to share your thoughts!

Access Paper
View Source PDF
Submission Info
Date:
Sep 23, 2026
Topic:
Computer Vision
Area:
Computer Vision
Comments:
0
Bookmark
ฯ†-RIE: From Photorealistic Reconstruction to Interactive Environments | Researchia