# VGGT-Bridge: Beyond Sequential Pose Graphs via Coarse-Stride Skip Edges

arXiv: https://arxiv.org/abs/2610.06594 · HTML: https://mlsanity.com/paper/2610.06594/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 55 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Builds on (most cited first, 10 of 10)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [π3: Permutation-Equivariant Visual Geometry Learning](https://mlsanity.com/paper/2507.13347/) (2025)
- [BA-Net: Dense Bundle Adjustment Network](https://mlsanity.com/paper/1806.04807/) (2018)
- [Streaming 4D Visual Geometry Transformer](https://mlsanity.com/paper/2507.11539/) (2025)
- [TTT3R: 3D Reconstruction as Test-Time Training](https://mlsanity.com/paper/2509.26645/) (2025)
- [VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences](https://mlsanity.com/paper/2507.16443/) (2025)
- [LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory](https://mlsanity.com/paper/2603.03269/) (2026)
- [Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction](https://mlsanity.com/paper/2604.08542/) (2026)
- [LongStream: Long-Sequence Streaming Autoregressive Visual Geometry](https://mlsanity.com/paper/2602.13172/) (2026)
- [VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistency](https://mlsanity.com/paper/2602.05508/) (2026)

## Abstract (arXiv)

Feed-forward visual geometry transformers such as VGGT reconstruct dense 3D structure from images in a single forward pass, simplifying multi-view 3D reconstruction. However, their quadratic attention complexity makes them difficult to scale to long sequences with thousands of frames. Chunk-and-align frameworks address this by splitting a long sequence into overlapping chunks and stitching their local reconstructions into a pose graph. Yet existing methods connect only sequentially adjacent chunks, so small per-frame errors accumulate along the chain into large-scale drift. To move beyond sequential edges, we propose VGGT-Bridge, which adds long-range skip edges that directly constrain non-adjacent chunks without retraining. By running VGGT on sparsely sampled coarse chunks, each coarse chunk bridges distant fine chunks into a single direct constraint. We further turn VGGT's first-frame scale bias into a drift correction by feeding selected coarse chunks in reverse, and a loop-aware policy keeps this reversal compatible with existing loop closures. VGGT-Bridge reduces ATE by 28.3% on KITTI Odometry, 18.8% on Virtual KITTI, and 10.0% on Waymo Open over the SwiftVGGT baseline, achieving the best performance among all chunk-and-align methods.