SceneExpander: Expanding 3D Scenes with Free-Form Inserted Views

TL;DR

SceneExpander enables iterative 3D scene extension by synthesizing and integrating new views with test-time adaptation, maintaining multi-view consistency despite misalignments.

Contribution

It introduces a novel test-time adaptation method for 3D reconstruction that stabilizes original scenes while integrating misaligned inserted views.

Findings

Improved scene expansion and reconstruction quality on ETH scenes.

Effective handling of view misalignments during scene extension.

Demonstrated robustness in online data experiments.

Abstract

World building with 3D scene representations is increasingly important for content creation, simulation, and interactive experiences, yet real workflows are inherently iterative: creators must repeatedly extend an existing scene under user control. Motivated by this research gap, we study 3D scene expansion in a user-centric workflow: starting from a real scene captured by multi-view images, we extend its coverage by inserting an additional view synthesized by a generative model. Unlike simple object editing or style transfer in a fixed scene, the inserted view is often 3D-misaligned with the original reconstruction, introducing geometry shifts, hallucinated content, or view-dependent artifacts that break global multi-view consistency. To address the 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 original scene by distilling geometric cues from the captured views, while inserted-view self-distillation preserves observation-supported predictions yet adapts latent geometry and appearance to accommodate the misaligned inserted view. Experiments on ETH scenes and online data demonstrate improved expansion behavior and reconstruction quality under misalignment.