We present a novel human-in-the-loop approach to estimate 3D scene layout that uses human feedback from an egocentric standpoint. We study this approach through introduction of a novel local correction task, where users identify local errors and prompt a model to automatically correct them. Building on SceneScript, a state-of-the-art framework for 3D scene layout estimation that leverages structured language, we propose a solution that structures this problem as "infilling", a task studied in natural language processing. We train a multi-task version of SceneScript that maintains performance on global predictions while significantly improving its local correction ability. We integrate this into a human-in-the-loop system, enabling a user to iteratively refine scene layout estimates via a low-friction "one-click fix'' workflow. Our system enables the final refined layout to diverge from the training distribution, allowing for more accurate modelling of complex layouts.
@article{arxiv.2503.11806,
title = {Human-in-the-Loop Local Corrections of 3D Scene Layouts via Infilling},
author = {Christopher Xie and Armen Avetisyan and Henry Howard-Jenkins and Yawar Siddiqui and Julian Straub and Richard Newcombe and Vasileios Balntas and Jakob Engel},
journal= {arXiv preprint arXiv:2503.11806},
year = {2025}
}