cs.CVOct 31, 2026

SceneBound: How Much Should a Streaming 3D Reconstruction Model Remember?

Authors: Ziming Wang, Chuyue Gong, Chutian Wang, Jingmin Zhu, Hongliang Cao, Yuheng He, Xiuyu Li

Organizations: The Hong Kong University of Science and Technology · Sun Yat-sen University · Monash University · Beihang University · 

Abstract

Streaming 3D reconstruction models keep past video frames in a recurrent state, fast weights from test-time training, or a key-value (KV) cache. Each written frame shifts the coordinate frame of later cameras or occupies GPU memory. Training-free rules decide what to write from a signal of the current frame. How much they write accounts for their mean accuracy: spending the update budget of a gate at uniformly spaced frames, with no signal, matches nine published gates, and the budget bounds the drift of the state wherever the writes fall. We propose SceneBound, a training-free rule that writes a frame only when its predicted camera pose lies at least a fixed radius from every stored keyframe. Its keyframe count stays within a constant factor of the covering number of the visited poses, the fewest views that keep a keyframe near every camera, so the count grows with the places visited and stays flat when the camera returns. In large scenes, SceneBound closes a submap once decoding its first frame again reveals drift. SceneBound uses one radius across four released models and three memory types. In the recurrent state of CUT3R and the KV cache of StreamVGGT, it achieves the lowest mean trajectory error among the published training-free rules we evaluate, in one pass and over nine passes of a scene, where its keyframes grow by 3% to 6%.

Explore similar work

CardsList
  1. Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction

    May 16, 2026Kejun Ren, Lei Jin, Tianxin Huang +2Streaming 3D Reconstruction3D Reconstruction

  2. SSR: A Training-Free Approach for Streaming 3D Reconstruction

    Mar 16, 2026Hui Deng, Yuxin Mao, Yuxin He +1Streaming 3D Reconstruction3D Reconstruction

  3. ReCal3R: Reliability-Calibrated Learning Rates for Streaming 3D Reconstruction

    Jul 6, 2026Xinze Li, Yiyuan Wang, Pengxu Chen +4Streaming 3D Reconstruction3D Scene Representation