Lyra 2.0 produces persistent 3D-consistent video sequences for large explorable worlds by using per-frame geometry for information routing and self-augmented training to correct temporal drift.
Spatia: Video generation with updatable spatial memory
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
fields
cs.CV 3years
2026 3roles
background 3polarities
background 3representative citing papers
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
citing papers explorer
-
Lyra 2.0: Explorable Generative 3D Worlds
Lyra 2.0 produces persistent 3D-consistent video sequences for large explorable worlds by using per-frame geometry for information routing and self-augmented training to correct temporal drift.
-
Evolution of Video Generative Foundations
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
- World-R1: Reinforcing 3D Constraints for Text-to-Video Generation