# LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

arXiv: https://arxiv.org/abs/2603.03269 · HTML: https://mlsanity.com/paper/2603.03269/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 59 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Builds on (most cited first, 30 of 49)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [Linear Transformers Are Secretly Fast Weight Programmers](https://mlsanity.com/paper/2102.11174/) (2021)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [Learning to (Learn at Test Time): RNNs with Expressive Hidden States](https://mlsanity.com/paper/2407.04620/) (2024)
- [Virtual KITTI 2](https://mlsanity.com/paper/2001.10773/) (2020)
- [π3: Permutation-Equivariant Visual Geometry Learning](https://mlsanity.com/paper/2507.13347/) (2025)
- [MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision](https://mlsanity.com/paper/2410.19115/) (2024)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos](https://mlsanity.com/paper/2412.04463/) (2024)
- [Flex Attention: A Programming Model for Generating Optimized Attention Kernels](https://mlsanity.com/paper/2412.05496/) (2024)
- [ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals](https://mlsanity.com/paper/1905.02082/) (2019)
- [Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo](https://mlsanity.com/paper/2303.01943/) (2023)

## Built on by (most cited first, 30 of 39)

- [LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction](https://mlsanity.com/paper/2604.14141/) (2026)
- [VGGT-Omega](https://mlsanity.com/paper/2605.15195/) (2026)
- [MemoryWAM: Efficient World Action Modeling with Persistent Memory](https://mlsanity.com/paper/2606.20562/) (2026)
- [HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction](https://mlsanity.com/paper/2605.23889/) (2026)
- [MeMix: Writing Less, Remembering More for Streaming 3D Reconstruction](https://mlsanity.com/paper/2603.15330/) (2026)
- [Mem3R: Streaming 3D Reconstruction with Hybrid Memory via Test-Time Training](https://mlsanity.com/paper/2604.07279/) (2026)
- [Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective](https://mlsanity.com/paper/2604.14025/) (2026)
- [Glob3R: Global Structure-from-Motion with 3D Foundation Models](https://mlsanity.com/paper/2607.09225/) (2026)
- [OpenWorldLib: A Unified Codebase and Definition of Advanced World Models](https://mlsanity.com/paper/2604.04707/) (2026)
- [Fast Spatial Memory with Elastic Test-Time Training](https://mlsanity.com/paper/2604.07350/) (2026)
- [Mamba-VGGT: Persistent Long-Sequence Video Geometry Grounded Transformer via External Sliding Window Mamba Memory](https://mlsanity.com/paper/2605.17478/) (2026)
- [R3: 3D Reconstruction via Relative Regression](https://mlsanity.com/paper/2605.26519/) (2026)
- [G3T Up! Gravity Aligned Coordinate Frames Simplify Pointmap Processing](https://mlsanity.com/paper/2605.27372/) (2026)
- [Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping](https://mlsanity.com/paper/2606.05035/) (2026)
- [VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion](https://mlsanity.com/paper/2607.27194/) (2026)
- [SS3D: End2End Self-Supervised 3D from Web Videos](https://mlsanity.com/paper/2604.22686/) (2026)
- [Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction](https://mlsanity.com/paper/2605.16981/) (2026)
- [Compressing History into Memory: Distilling Transformers into Recurrent Transformers](https://mlsanity.com/paper/2606.21562/) (2026)
- [SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers](https://mlsanity.com/paper/2607.03612/) (2026)
- [Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction](https://mlsanity.com/paper/2608.27529/) (2026)
- [GeoFF3D: Coordinate-Anchored Feed-Forward Reconstruction for Large-Scale UAV Mapping](https://mlsanity.com/paper/2608.28288/) (2026)
- [Point4D: Long-range 4D Motion Reconstruction](https://mlsanity.com/paper/2609.09145/) (2026)
- [Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation](https://mlsanity.com/paper/2609.20744/) (2026)
- [LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos](https://mlsanity.com/paper/2605.17303/) (2026)
- [Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration](https://mlsanity.com/paper/2605.22814/) (2026)
- [Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers](https://mlsanity.com/paper/2605.23892/) (2026)
- [SpatialBench: Is Your Spatial Foundation Model an All-Round Player?](https://mlsanity.com/paper/2605.27367/) (2026)
- [Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning](https://mlsanity.com/paper/2606.00963/) (2026)
- [Online Neural Space Time Memory for Dynamic Novel View Synthesis](https://mlsanity.com/paper/2607.15271/) (2026)
- [VI3: Grounding Pretrained 3D Foundation Models with Inertial Cues](https://mlsanity.com/paper/2609.03824/) (2026)

## Abstract (arXiv)

Feedforward geometric foundation models achieve strong short-window reconstruction, yet scaling them to minutes-long videos is bottlenecked by quadratic attention complexity or limited effective memory in recurrent designs. We present LoGeR (Long-context Geometric Reconstruction), a novel architecture that scales dense 3D reconstruction to extremely long sequences without post-optimization. LoGeR processes video streams in chunks, leveraging strong bidirectional priors for high-fidelity intra-chunk reasoning. To manage the critical challenge of coherence across chunk boundaries, we propose a learning-based hybrid memory module. This dual-component system combines a parametric Test-Time Training (TTT) memory to anchor the global coordinate frame and prevent scale drift, alongside a non-parametric Sliding Window Attention (SWA) mechanism to preserve uncompressed context for high-precision adjacent alignment. Remarkably, this memory architecture enables LoGeR to be trained on sequences of 128 frames, and generalize up to thousands of frames during inference. Evaluated across standard benchmarks and a newly repurposed VBR dataset with sequences of up to 19k frames, LoGeR substantially outperforms prior state-of-the-art feedforward methods--reducing ATE on KITTI by over 74%--and achieves robust, globally consistent reconstruction over unprecedented horizons.