VGGT-Bridge: Beyond Sequential Pose Graphs via Coarse-Stride Skip Edges
cs.CV
Submitted: 2026-10-05
Updated: 2026-10-05
Sources
- TTT3R: 3D Reconstruction as Test-Time Training
- LongStream: Long-Sequence Streaming Autoregressive Visual Geometry
- VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences
- DINOv2: Learning Robust Visual Features without Supervision
- BA-Net: Dense Bundle Adjustment Network
- $\pi^3$: Permutation-Equivariant Visual Geometry Learning
- Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction
- VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistency
- LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory
- Streaming 4D Visual Geometry Transformer
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models