SceneBound:ストリーミング3D再構成モデルはどこまで記憶すべきか
SceneBound: How Much Should a Streaming 3D Reconstruction Model Remember?
カメラ姿勢が既存キーフレームから一定距離離れたときだけフレームを書き込む学習不要のルールを提案し、大規模シーンでの軌跡誤差を低減しつつメモリ増加を抑えた。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Ziming Wang, Chuyue Gong, Chutian Wang, Jingmin Zhu, Hongliang Cao, Yuheng He, Xiuyu Li
分類: cs.CV, cs.RO
原文アブストラクト
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%.