AI RESEARCH
Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction
arXiv CS.CV
•
ArXi:2605.16981v1 Announce Type: new Streaming 3D reconstruction under a strict constant-memory budget hinges on how the recurrent state is updated as the stream evolves. We profile TTT3R-style per-token gates across five benchmarks and discover a structural bottleneck: the gate is intrinsically bounded in magnitude (median $0.31$; never exceeding $0.6$) and nearly frame-invariant, yielding an effective memory horizon of only $\sim$3 frames per state token, which serves as the structural origin of long-sequence drift.