Mamba-VGGT introduces a Sliding Window Mamba memory module and Zero-Init Spatial Memory Injector to enable persistent long-range geometric reasoning in VGGT for extended video sequences.
Refusion: 3d reconstruction in dynamic environments for rgb-d cameras exploiting residuals
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
FrameVGGT replaces token-level KV retention with frame-level segments and prototypes to bound memory while preserving geometric coherence in streaming VGGT.
A closed-form scalar frame-level gate α_t derived from internal feature changes extends effective memory in recurrent 3D reconstruction and improves accuracy on long sequences up to 4541 frames.
citing papers explorer
-
Mamba-VGGT: Persistent Long-Sequence Video Geometry Grounded Transformer via External Sliding Window Mamba Memory
Mamba-VGGT introduces a Sliding Window Mamba memory module and Zero-Init Spatial Memory Injector to enable persistent long-range geometric reasoning in VGGT for extended video sequences.
-
FrameVGGT: Geometry-Aligned Frame-Level Memory for Bounded Streaming VGGT
FrameVGGT replaces token-level KV retention with frame-level segments and prototypes to bound memory while preserving geometric coherence in streaming VGGT.
-
Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction
A closed-form scalar frame-level gate α_t derived from internal feature changes extends effective memory in recurrent 3D reconstruction and improves accuracy on long sequences up to 4541 frames.