TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction

TL;DR

TTSA3R is a training-free framework that improves long-term 3D reconstruction by adaptively updating persistent states using temporal and spatial cues, reducing catastrophic forgetting over extended sequences.

Contribution

It introduces a novel training-free approach with modules for temporal and spatial adaptive updates, enhancing long-term stability in streaming 3D reconstruction.

Findings

Significantly reduces error increase on extended sequences

Outperforms baseline models in long-term reconstruction stability

Effective across diverse 3D reconstruction tasks

Abstract

Streaming recurrent models enable efficient 3D reconstruction by maintaining persistent state representations. However, they suffer from catastrophic forgetting over long sequences due to balancing historical information with new observations. Recent methods alleviate this by deriving adaptive signals from attention perspective, but they operate on single dimensions without considering temporal and spatial consistency. To this end, we propose a training-free framework termed TTSA3R that leverages both temporal state evolution and spatial observation quality for adaptive state updates in 3D reconstruction. In particular, we devise a Temporal Adaptive Update Module that regulates update magnitude by analyzing temporal state evolution patterns. Then, a Spatial Contextual Update Module is introduced to localize spatial regions that require updates through observation-state alignment and scene dynamics. These complementary signals are finally fused to determine the state updating strategies. Extensive experiments demonstrate the effectiveness of TTSA3R in diverse 3D tasks. Moreover, our method exhibits only 1.33x error increase compared to over 4x degradation in the baseline model on extended sequences of 3D reconstruction, significantly improving long-term reconstruction stability. Our codes are available at https://github.com/anonus2357/ttsa3r.