Search papers, labs, and topics across Lattice.
HY-World 2.0 is a multi-modal world model that generates navigable 3D Gaussian Splatting scenes from text, single-view images, multi-view images, or videos. It achieves this through a four-stage pipeline involving panorama generation, trajectory planning, world expansion via keyframe-based view generation with consistent memory, and world composition using a feed-forward 3D prediction model. The system also introduces WorldLens, a high-performance 3DGS rendering platform, and achieves state-of-the-art performance among open-source approaches, rivaling closed-source models.
Imagine creating high-fidelity, navigable 3D worlds from just a text prompt or a single image – HY-World 2.0 makes it a reality.
We introduce HY-World 2.0, a multi-modal world model framework that advances our prior project HY-World 1.0. HY-World 2.0 accommodates diverse input modalities, including text prompts, single-view images, multi-view images, and videos, and produces 3D world representations. With text or single-view image inputs, the model performs world generation, synthesizing high-fidelity, navigable 3D Gaussian Splatting (3DGS) scenes. This is achieved through a four-stage method: a) Panorama Generation with HY-Pano 2.0, b) Trajectory Planning with WorldNav, c) World Expansion with WorldStereo 2.0, and d) World Composition with WorldMirror 2.0. Specifically, we introduce key innovations to enhance panorama fidelity, enable 3D scene understanding and planning, and upgrade WorldStereo, our keyframe-based view generation model with consistent memory. We also upgrade WorldMirror, a feed-forward model for universal 3D prediction, by refining model architecture and learning strategy, enabling world reconstruction from multi-view images or videos. Also, we introduce WorldLens, a high-performance 3DGS rendering platform featuring a flexible engine-agnostic architecture, automatic IBL lighting, efficient collision detection, and training-rendering co-design, enabling interactive exploration of 3D worlds with character support. Extensive experiments demonstrate that HY-World 2.0 achieves state-of-the-art performance on several benchmarks among open-source approaches, delivering results comparable to the closed-source model Marble. We release all model weights, code, and technical details to facilitate reproducibility and support further research on 3D world models.
Tsinghua AI