WonderJourney

Going from Anywhere to Everywhere

CVPR 2024

We introduce WonderJourney, a modularized framework for perpetual scene generation. Unlike prior work on view generation that focuses on a single type of scenes, we start at any user-provided location (by a text description or an image), and generate a journey through a long sequence of diverse yet coherently connected 3D scenes. We leverage an LLM to generate textual descriptions of the scenes in this journey, a text-driven point cloud generation pipeline to make a compelling and coherent sequence of 3D scenes, and a large VLM to verify the generated scenes. We show compelling, diverse visual results across various scene types and styles, forming imaginary ``wonderjourneys''.

No, no! The adventures first, explanations take such a dreadful time. --- Alice's Adventures in Wonderland

Our modular design does not require any training, allowing easy future improvements from the quick advances in vision and language models.

• [CVPR2025] WonderWorld: Interactive 3D Scene Generation from a Single Image
• [ICCV2025] WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions
• [ICCV2025] WorldScore: A Unified Evaluation Benchmark for World Generation

@inproceedings{yu2024wonderjourney, title={Wonderjourney: Going from Anywhere to Everywhere}, author={Hong-Xing Yu and Haoyi Duan and Junhwa Hur and Kyle Sargent and Michael Rubinstein and William T. Freeman and Forrester Cole and Deqing Sun and Noah Snavely and Jiajun Wu and Charles Herrmann}, booktitle={CVPR}, year={2024} }