Edit-As-Act: Goal-Regressive Planning for Open-Vocabulary 3D Indoor Scene Editing

TL;DR

This paper introduces Edit-As-Act, a goal-regressive planning framework for open-vocabulary 3D indoor scene editing that ensures minimal, physically consistent modifications aligned with natural language instructions.

Contribution

It proposes a novel planning-based approach using symbolic goal predicates and a PDDL-inspired language to improve scene editing fidelity and physical plausibility.

Findings

Outperforms prior methods on E2A-Bench across all tasks

Achieves high instruction fidelity and semantic consistency

Ensures physically coherent scene transformations

Abstract

Editing a 3D indoor scene from natural language is conceptually straightforward but technically challenging. Existing open-vocabulary systems often regenerate large portions of a scene or rely on image-space edits that disrupt spatial structure, resulting in unintended global changes or physically inconsistent layouts. These limitations stem from treating editing primarily as a generative task. We take a different view. A user instruction defines a desired world state, and editing should be the minimal sequence of actions that makes this state true while preserving everything else. This perspective motivates Edit-As-Act, a framework that performs open-vocabulary scene editing as goal-regressive planning in 3D space. Given a source scene and free-form instruction, Edit-As-Act predicts symbolic goal predicates and plans in EditLang, a PDDL-inspired action language that we design with explicit preconditions and effects encoding support, contact, collision, and other geometric relations. A language-driven planner proposes actions, and a validator enforces goal-directedness, monotonicity, and physical feasibility, producing interpretable and physically coherent transformations. By separating reasoning from low-level generation, Edit-As-Act achieves instruction fidelity, semantic consistency, and physical plausibility - three criteria that existing paradigms cannot satisfy together. On E2A-Bench, our benchmark of 63 editing tasks across 9 indoor environments, Edit-As-Act significantly outperforms prior approaches across all edit types and scene categories.