# SceneExpander: Text-Guided 3D Scene Expansion via Free-Form View Insertion

Source: [SceneExpander: Text-Guided 3D Scene Expansion via Free-Form View Insertion](<https://www.sota2.com/research/paper/69cb54ea0636e5bf4afc9d63>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-31T05:00:01.455Z

Authors: Zijian He, Renjie Liu, Yihao Wang, Weizhi Zhong, Huan Yuan, Kun Gai, Guangrun Wang, Guanbin Li

Published: 2026-03-28T02:04:48.000Z

## Abstract

World building with 3D scene representations is increasingly important for content creation, simulation, and interactive experiences, yet real workflows are inherently iterative: creators repeatedly extend existing scenes under user control. Motivated by this gap, we study text-guided 3D scene expansion via free-form view insertion. Starting from a real scene captured by multi-view images, a user specifies a text expansion intent, which a generative model materializes as an inserted view extending the scene coverage. Unlike simple object editing or style transfer within a fixed scene, the inserted view may be 3D-misaligned with the original reconstruction, introducing geometric shifts, hallucinated content, or view-dependent artifacts that disrupt global multi-view consistency. To address this challenge, we propose SceneExpander, which applies test-time adaptation to a parametric feed-forward 3D reconstruction model with two complementary distillation signals: anchor distillation stabilizes the captured scene using geometric cues from the captured views, while inserted-view self-distillation retains insertion-supported predictions to accommodate the misaligned view. Experiments on ETH scenes and online data demonstrate improved expansion behavior and reconstruction quality under misalignment.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Scene Expansion on ETH and online collections](<https://www.sota2.com/research/sota/3d-scene-expansion-on-eth-and-online-collections.md>): 3D Scene Expansion; ETH and online collections; PSNR: 21.206.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.27084>)

[PDF](<https://arxiv.org/pdf/2603.27084.pdf>)