Endless World: Real-Time 3D-Aware Long Video Generation

TL;DR

Endless World is a real-time framework for generating infinite, 3D-consistent videos by combining autoregressive training, global 3D-aware attention, and a 3D injection mechanism, enabling stable long-horizon video synthesis.

Contribution

The paper introduces a novel real-time 3D-aware video generation method that supports infinite sequences with long-range coherence and geometric consistency.

Findings

Produces long, stable, and coherent videos

Achieves real-time inference on a single GPU

Outperforms existing methods in visual fidelity and spatial consistency

Abstract

Producing long, coherent video sequences with stable 3D structure remains a major challenge, particularly in streaming scenarios. Motivated by this, we introduce Endless World, a real-time framework for infinite, 3D-consistent video generation.To support infinite video generation, we introduce a conditional autoregressive training strategy that aligns newly generated content with existing video frames. This design preserves long-range dependencies while remaining computationally efficient, enabling real-time inference on a single GPU without additional training overhead.Moreover, our Endless World integrates global 3D-aware attention to provide continuous geometric guidance across time. Our 3D injection mechanism enforces physical plausibility and geometric consistency throughout extended sequences, addressing key challenges in long-horizon and dynamic scene synthesis.Extensive experiments demonstrate that Endless World produces long, stable, and visually coherent videos, achieving competitive or superior performance to existing methods in both visual fidelity and spatial consistency. Our project has been available on https://bwgzk-keke.github.io/EndlessWorld/.