SceneBound: How Much Should a Streaming 3D Reconstruction Model Remember?
Overview
This paper introduces SceneBound, a training-free rule for streaming 3D reconstruction that determines when to write frames based on camera pose distance from stored keyframes. The method keeps the keyframe count within a constant factor of the covering number of visited poses and achieves the lowest mean trajectory error among nine evaluated training-free rules across four models and three memory types, with keyframe growth between 3% and 6%.
Generated from attributed reports · Updated 1 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · memory types: 3 other · Basis not reported
“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 trajec”
Exact source · revision 1Source owner not reported
Reported quantity · gates compared: 9 other · Basis not reported
“ng 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”
Exact source · revision 1Source owner not reported
Reported quantity · scene passes evaluated: 1 other · reported trials · Differing source assertions
“tory 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%.”
Exact source · revision 1Source owner not reported
Reported quantity · scene passes evaluated: 9 other · reported trials · Differing source assertions
“tory 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%.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalSceneBound: How Much Should a Streaming 3D Reconstruction Model Remember?
This paper introduces SceneBound, a training-free rule for streaming 3D reconstruction that determines when to write frames based on camera pose distance from stored keyframes. The method keeps the keyframe count within a constant factor of the covering number of visited poses and achieves the lowest mean trajectory error among nine evaluated training-free rules across four models and three memory types, with keyframe growth between 3% and 6%.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).