AMB3R-SLAM: Kilometer-scale SLAM with Hierarchical Backend

arXiv:2609.19518 · cs.CV, cs.RO · Submitted 2026-09-17 · Read on arXiv

cs.CV, cs.RO

Submitted: 2026-09-17

Updated: 2026-09-17

Project page: https://hengyiwang.github.io/projects/amber-slam

Terminology

• Foundation Model — 17× in this paper · explained in 3 episodes
• Foundation Models — 12× in this paper · explained in 7 episodes
• Consistency — 11× in this paper · explained in 3 episodes
• AUC — 9× in this paper · explained in 2 episodes
• Transformer — 8× in this paper · explained in 2 episodes
• Visual Odometry — 8× in this paper
• Conference on Computer Vision and Pattern Recognition — 7× in this paper
• Accuracy — 6× in this paper · explained in 1 episode
• Robustness — 5× in this paper · explained in 5 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Benchmark — 4× in this paper · explained in 2 episodes
• Gaussian Splatting — 4× in this paper · explained in 4 episodes
• European Conference on Computer Vision — 3× in this paper
• Fidelity — 3× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• 3D Gaussian Splatting — 1× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• IEEE International Conference on Robotics and Automation — 1× in this paper
• International Symposium on Mixed and Augmented Reality — 1× in this paper
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Point Clouds — 1× in this paper · explained in 2 episodes
• Transactions on Pattern Analysis and Machine Intelligence — 1× in this paper
• Verification — 1× in this paper · explained in 2 episodes
• Visual Simultaneous Localization and Mapping — 1× in this paper

Sources

• Dens3R: A Foundation Model for 3D Geometry Prediction
• Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving
• ViPE: Video Pose Engine for 3D Geometric Perception
• Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
• G3T Up! Gravity Aligned Coordinate Frames Simplify Pointmap Processing
• Geometric Context Transformer for Streaming 3D Reconstruction
• TTT3R: 3D Reconstruction as Test-Time Training
• LONG3R: Long Sequence Streaming 3D Reconstruction
• SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization
• Glob3R: Global Structure-from-Motion with 3D Foundation Models
• VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences
• VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction
• VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold
• Evict3R: Training-Free Token Eviction for Memory-Bounded Streaming Visual Geometry Transformers
• Can Video Diffusion Model Reconstruct 4D Geometry?
• MapAnything: Universal Feed-Forward Metric 3D Reconstruction
• G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration
• STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer
• StereoDiff: Stereo-Diffusion Synergy for Video Depth Estimation
• WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

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