WonderWorld: Interactive 3D Scene Generation from a Single Image

TL;DR

WonderWorld is a fast, interactive framework for generating 3D scenes from a single image, enabling real-time user interaction and exploration with high speed and coherence.

Contribution

The paper introduces FLAGS, a novel scene representation, and a guided depth diffusion method, significantly reducing 3D scene generation time from a single view.

Findings

Generates connected 3D scenes in less than 10 seconds.

Enables real-time interactive scene creation and exploration.

Achieves high coherence and diversity in generated scenes.

Abstract

We present WonderWorld, a novel framework for interactive 3D scene generation that enables users to interactively specify scene contents and layout and see the created scenes in low latency. The major challenge lies in achieving fast generation of 3D scenes. Existing scene generation approaches fall short of speed as they often require (1) progressively generating many views and depth maps, and (2) time-consuming optimization of the scene geometry representations. We introduce the Fast Layered Gaussian Surfels (FLAGS) as our scene representation and an algorithm to generate it from a single view. Our approach does not need multiple views, and it leverages a geometry-based initialization that significantly reduces optimization time. Another challenge is generating coherent geometry that allows all scenes to be connected. We introduce the guided depth diffusion that allows partial conditioning of depth estimation. WonderWorld generates connected and diverse 3D scenes in less than 10 seconds on a single A6000 GPU, enabling real-time user interaction and exploration. We demonstrate the potential of WonderWorld for user-driven content creation and exploration in virtual environments. We release full code and software for reproducibility. Project website: https://kovenyu.com/WonderWorld/.