online-neural-space-time-memory-for-dynamic-novel-view-synthesis-eef113b5·1 events·first seen Aliases: Online Neural Space Time Memory for Dynamic Novel View Synthesis
A new arXiv preprint proposes a neural memory architecture for real-time novel view synthesis from multi-view streaming video of dynamic scenes. The method decouples memory update frequency from memory application frequency, using periodic gradient-based updates with per-frame cross-view attention to handle deformations. Two mechanisms — an auxiliary Memory Loss and a Memory Caching strategy — prevent catastrophic forgetting over long contexts. The approach achieves state-of-the-art performance on dynamic human motion scenes with minute-scale online memorization at real-time speeds.