CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction

arXiv:2610.01927 · cs.CV, cs.RO · Submitted 2026-10-01 · Read on arXiv

cs.CV, cs.RO

Submitted: 2026-10-01

Updated: 2026-10-01

Code: https://github.com/MoyangLi00/CLoSeR

Terminology

• Alignment — 17× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 9× in this paper
• Point Clouds — 9× in this paper · explained in 2 episodes
• Benchmark — 7× in this paper · explained in 2 episodes
• Consistency — 7× in this paper · explained in 3 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Transformer — 6× in this paper · explained in 2 episodes
• Absolute Trajectory Error — 5× in this paper
• Gaussian Splatting — 5× in this paper · explained in 4 episodes
• Robustness — 5× in this paper · explained in 5 episodes
• Test-Time Training — 5× in this paper
• Ablation — 3× in this paper · explained in 1 episode
• Foundation Model — 3× in this paper · explained in 3 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• 3D Gaussian Splatting — 2× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Decode — 2× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Optimal Transport — 1× in this paper · explained in 5 episodes
• Pattern Analysis and Machine Intelligence — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes
• Simultaneous Localization and Mapping — 1× in this paper
• Sliding Window Attention — 1× in this paper

Sources

• Geometric Context Transformer for Streaming 3D Reconstruction
• Easi3R: Estimating Disentangled Motion from DUSt3R Without Training
• TTT3R: 3D Reconstruction as Test-Time Training
• VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences
• D2-Net: A Trainable CNN for Joint Detection and Description of Local Features
• VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale
• ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training
• OKVIS2: Realtime Scalable Visual-Inertial SLAM with Loop Closure
• SlideSLAM: Sparse, Lightweight, Decentralized Metric-Semantic SLAM for Multi-Robot Navigation
• VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction
• VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold
• DINOv2: Learning Robust Visual Features without Supervision
• FastVGGT: Training-Free Acceleration of Visual Geometry Transformer
• Learning to (Learn at Test Time): RNNs with Expressive Hidden States
• DeepV2D: Video to Depth with Differentiable Structure from Motion
• AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend
• $\pi^3$: Permutation-Equivariant Visual Geometry Learning
• InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams
• MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
• LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

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