paper-with-me

홈 › Papers

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

2025-12-13 · Ke Zhang, Yiqun Mei, Jiacong Xu, Vishal M. Patel arxiv

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/.

📄 PDF Abstract BibTeX arXiv:2512.12430

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Similar Papers 제목 키워드 기반

An Endless Optical Phase Delay for Phase Synchronization in High-Capacity DCIs

2021-06-17 · Rakesh Ashok, Sana Naaz, Shalabh Gupta

In this work, we propose and demonstrate a module to linearly add an arbitrary amount of continuous (reset-free) phase delay to an optical signal. The proposed endless optical phase delay (EOPD) uses an optical IQ modula…

Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents

2023-09-29 · Marco Pleines, Matthias Pallasch, Frank Zimmer, Mike Preuss

Memory Gym presents a suite of 2D partially observable environments, namely Mortar Mayhem, Mystery Path, and Searing Spotlights, designed to benchmark memory capabilities in decision-making agents. These environments, or…

Decision MakingDeep Reinforcement Learning

Ergodic Risk Measures: Towards a Risk-Aware Foundation for Continual Reinforcement Learning

2025-10-03 · Juan Sebastian Rojas, Chi-Guhn Lee arxiv

Continual reinforcement learning (continual RL) seeks to formalize the notions of lifelong learning and endless adaptation in RL. In particular, the aim of continual RL is to develop RL agents that can maintain a careful…

Reinforcement LearningContinual Learning

CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives

2026-05-12 · Yihao Meng, Zichen Liu, Hao Ouyang, Qiuyu Wang 외 arxiv

Autoregressive video generation aims at real-time, open-ended synthesis. Yet, cinematic storytelling is not merely the endless extension of a single scene; it requires progressing through evolving events, viewpoint shift…

Video Generation

State Space Closure: Revisiting Endless Online Level Generation via Reinforcement Learning

2022-12-06 · Ziqi Wang, Tianye Shu, Jialin Liu

In this paper, we revisit endless online level generation with the recently proposed experience-driven procedural content generation via reinforcement learning (EDRL) framework. Inspired by an observation that EDRL tends…

Diversityreinforcement-learningReinforcement LearningReinforcement Learning (RL)