FILT3R: פילטר עדפי למצב סמוי לשיקוף 3D בזרימה

תקציר מקורי באנגליתarXiv:2603.18493v2 Announce Type: replace-cross Abstract: Streaming 3D reconstruction maintains a persistent latent state that is updated online from incoming frames, enabling constant-memory inference. A key failure mode is the state update rule: aggressive overwrites forget useful history, while conservative updates fail to track new evidence, and both behaviors become unstable beyond the training horizon. To address this challenge, we propose FILT3R, a training-free latent filtering layer that casts recurrent state updates as stochastic state estimation in token space. FILT3R maintains a per-token variance and computes a Kalman-style gain that adaptively balances memory retention against new observations. Process noise -- governing how much the latent state is expected to change between