STAC achieves a 10x memory reduction and 4x speedup for real-time streaming 3D reconstruction using spatio-temporal cache compression.
March 24, 2026
Original Paper
STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction
arXiv · 2603.20284
The Takeaway
It solves the linear memory growth bottleneck in causal transformers for 3D reconstruction. By compressing redundant spatial tokens into voxels and using attention-based temporal caching, it allows high-quality reconstruction on consumer-grade hardware that previously required enterprise memory budgets.
From the abstract
Online 3D reconstruction from streaming inputs requires both long-term temporal consistency and efficient memory usage. Although causal VGGT transformers address this challenge through a key-value (KV) cache mechanism, the cache grows linearly with the stream length, creating a major memory bottleneck. Under limited memory budgets, early cache eviction significantly degrades reconstruction quality and temporal consistency.In this work, we observe that attention in causal transformers for 3D reco