SSR: A Training-Free Approach for Streaming 3D Reconstruction
This addresses the problem of error accumulation in real-time 3D reconstruction for applications like robotics or AR/VR, though it is incremental as it builds on existing stateful recurrent models.
The paper tackles geometric drift in streaming 3D reconstruction by proposing SSR, a training-free operator that enforces Grassmannian sequence regularity, which reduces drift and improves reconstruction quality on long-sequence benchmarks.
Streaming 3D reconstruction demands long-horizon state updates under strict latency constraints, yet stateful recurrent models often suffer from geometric drift as errors accumulate over time. We revisit this problem from a Grassmannian manifold perspective: the latent persistent state can be viewed as a subspace representation, i.e., a point evolving on a Grassmannian manifold, where temporal coherence implies the state trajectory should remain on (or near) this manifold.Based on this view, we propose Self-expressive Sequence Regularization (SSR), a plug-and-play, training-free operator that enforces Grassmannian sequence regularity during inference.Given a window of historical states, SSR computes an analytical affinity matrix via the self-expressive property and uses it to regularize the current update, effectively pulling noisy predictions back toward the manifold-consistent trajectory with minimal overhead. Experiments on long-sequence benchmarks demonstrate that SSR consistently reduces drift and improves reconstruction quality across multiple streaming 3D reconstruction tasks.