Mamba-VGGT: Persistent Long-Sequence Video Geometry Grounded Transformer via External Sliding Window Mamba Memory

Documenti analoghi

• VGGT-Occ: Geometry-Grounded and Density-Aware Gated Fusion for 3D Occupancy Prediction
  di: Chen, Xun, et al.
  Pubblicazione: (2026)
• Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer
  di: Deng, Tianchen, et al.
  Pubblicazione: (2025)
• Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy
  di: Liu, Jiuming, et al.
  Pubblicazione: (2024)
• VGGT: Visual Geometry Grounded Transformer
  di: Wang, Jianyuan, et al.
  Pubblicazione: (2025)
• UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer
  di: Deng, Tianchen, et al.
  Pubblicazione: (2025)