FrameVGGT: Geometry-Aligned Frame-Level Memory for Bounded Streaming VGGT
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915942797148160 |
|---|---|
| author | Xu, Zhisong Oishi, Takeshi |
| author_facet | Xu, Zhisong Oishi, Takeshi |
| contents | Streaming Visual Geometry Transformers such as StreamVGGT enable strong online 3D perception, but their KV-cache grows unbounded over long streams, limiting practical deployment. We revisit bounded-memory streaming from the perspective of geometric support. Unlike language modeling, where useful information can often be compressed at the token level, geometry-driven reasoning depends on redundant and mutually compatible multi-view support. Under fixed budgets, token-level retention can fragment within-frame evidence, weaken the coherence of geometric support, and make stable long-horizon inference more difficult. Motivated by this observation, we propose FrameVGGT, a bounded explicit-memory framework that organizes each frame's incremental KV contribution as a coherent frame-level segment. FrameVGGT summarizes each segment with a lightweight key-space prototype and maintains a fixed-capacity memory of complementary segments, with an optional sparse anchor tier for difficult long-horizon intervals. Across long-sequence 3D reconstruction, video depth estimation, and camera pose estimation, FrameVGGT achieves favorable accuracy-memory trade-offs under bounded memory while maintaining more stable geometry over long streams. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07690 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FrameVGGT: Geometry-Aligned Frame-Level Memory for Bounded Streaming VGGT Xu, Zhisong Oishi, Takeshi Computer Vision and Pattern Recognition Streaming Visual Geometry Transformers such as StreamVGGT enable strong online 3D perception, but their KV-cache grows unbounded over long streams, limiting practical deployment. We revisit bounded-memory streaming from the perspective of geometric support. Unlike language modeling, where useful information can often be compressed at the token level, geometry-driven reasoning depends on redundant and mutually compatible multi-view support. Under fixed budgets, token-level retention can fragment within-frame evidence, weaken the coherence of geometric support, and make stable long-horizon inference more difficult. Motivated by this observation, we propose FrameVGGT, a bounded explicit-memory framework that organizes each frame's incremental KV contribution as a coherent frame-level segment. FrameVGGT summarizes each segment with a lightweight key-space prototype and maintains a fixed-capacity memory of complementary segments, with an optional sparse anchor tier for difficult long-horizon intervals. Across long-sequence 3D reconstruction, video depth estimation, and camera pose estimation, FrameVGGT achieves favorable accuracy-memory trade-offs under bounded memory while maintaining more stable geometry over long streams. |
| title | FrameVGGT: Geometry-Aligned Frame-Level Memory for Bounded Streaming VGGT |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.07690 |