Aug 31, 2026 · cs.CVJ/K move · Enter open · S save
Jingong Chen, Qingwen Zhang, Sanghyeon Jun, Chulwoo Pack+2
Department of Electrical Engineering & Computer Science, South Dakota State University, Brookings, SD, USA · Department of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, Sweden · Department of Built Environment, Aalto University, Espoo, Finland
Continuous-time 4D reconstruction remains impractical on standalone XR headsets. Per-scene optimization demands deployment-infeasible compute, and lower budgets cause collapse rather than degrade gradually. Feed-forward prediction is fast, but struggle to recover scene-specific detail. We present Amortized Anchor Refinement, which uses a frozen backbone to predict an initial Gaussian representation and a short optimization to specialize it under a fixed compute budget, with a capacity floor preserving representational density. A training-free stage then applies a persistent-homology constraint to prune unstable Gaussians while preserving topologically persistent structures, and streams the resulting trajectories directly as scene flow. On the Stage-Capture benchmark, Amortized Anchor Refinement achieves 24.31
±2.22dB, while our deployment experiments demonstrate reconstruction within the target budget on a single consumer GPU and playback on a standalone XR headset.