L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory
L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory
L3G-World uses compact latent 3D Gaussian memory and video diffusion Transformers to alternately perform autoregressive updates, generating spatially consistent interactive worlds in real time. The model grows memory with the scene range rather than the flow length by generating Gaussians in new areas and refining existing Gaussians, each storing VAE latent features that can be directly rendered into DiT's latent space.
Published on Oct 29
Authors:
,
,
,
,
,
,
Abstract
L3G-World uses a compact latent 3D Gaussian memory and alternating autoregressive updates with a video diffusion transformer to generate spatially consistent interactive worlds in real time.
Interactive world models generate visual content conditioned on user actions, yet maintaining spatial consistency over long-horizon exploration in real time remains challenging. Existing approaches rely on either temporal context or explicit 3D memory, both of which scale poorly because memory grows with the length of the generated stream. Moreover, explicit 3D memories condition latent video generators by re-encoding RGB renderings, which precludes real-time generation. In this paper, we introduce a Latent 3D Gaussian Memory (L3G) that combines the efficiency of feed-forward reconstruction with a compact, rapidly renderable scene representation. Building on this memory, we propose L3G-World, in which a memory updater and a video diffusion transformer (DiT) alternate autoregressively to generate spatially consistent worlds. The memory updater spawns Gaussians in newly observed regions and refines existing ones, so that the memory grows with scene extent rather than stream length. Each Gaussian further stores a VAE latent feature, allowing the memory to be rendered directly into the DiT's latent space without VAE re-encoding. Experiments show that L3G-World achieves state-of-the-art generation quality and long-horizon spatial consistency, with up to 38.6times fewer 3D primitives, 3.2times faster memory updates, and 359times faster memory rendering relative to the most efficient prior 3D-memory baseline for each metric, enabling real-time world generation at 9 FPS.
View arXiv page View PDF Project page GitHub 13 Add to collection
Get this paper in your agent:
hf papers read 2610.40614
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.40614 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.40614 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.40614 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
Source: Hugging Face Daily Papers · huggingface.co