# Online3R: Online Learning for Consistent Sequential Reconstruction Based on Geometry Foundation Model

arXiv: https://arxiv.org/abs/2604.09480 · HTML: https://mlsanity.com/paper/2604.09480/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 26 of 26)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [AdapterHub: A Framework for Adapting Transformers](https://mlsanity.com/paper/2007.07779/) (2020)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025)
- [Neural RGB-D Surface Reconstruction](https://mlsanity.com/paper/2104.04532/) (2021)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors](https://mlsanity.com/paper/2412.12392/) (2024)
- [DeepV2D: Video to Depth with Differentiable Structure from Motion](https://mlsanity.com/paper/1812.04605/) (2018)
- [MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion](https://mlsanity.com/paper/2409.19152/) (2024)
- [A Survey of Structure from Motion](https://mlsanity.com/paper/1701.08493/) (2017)
- [VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold](https://mlsanity.com/paper/2505.12549/) (2025)
- [GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction](https://mlsanity.com/paper/2309.02436/) (2023)
- [DeepFactors: Real-Time Probabilistic Dense Monocular SLAM](https://mlsanity.com/paper/2001.05049/) (2020)
- [SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos](https://mlsanity.com/paper/2412.09401/) (2024)
- [Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory](https://mlsanity.com/paper/2507.02863/) (2025)
- [Deep Patch Visual SLAM](https://mlsanity.com/paper/2408.01654/) (2024)
- [GeoCalib: Learning Single-image Calibration with Geometric Optimization](https://mlsanity.com/paper/2409.06704/) (2024)
- [Test3R: Learning to Reconstruct 3D at Test Time](https://mlsanity.com/paper/2506.13750/) (2025)
- [LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models](https://mlsanity.com/paper/2412.07746/) (2024)

## Built on by (most cited first, 1 of 1)

- [GeoWeaver: Accurate Long-Sequence 3D Reconstruction via Hierarchical Geometric Assembly](https://mlsanity.com/paper/2608.17389/) (2026)

## Abstract (arXiv)

We present Online3R, a new sequential reconstruction framework that is capable of adapting to new scenes through online learning, effectively resolving inconsistency issues. Specifically, we introduce a set of learnable lightweight visual prompts into a pretrained, frozen geometry foundation model to capture the knowledge of new environments while preserving the fundamental capability of the foundation model for geometry prediction. To solve the problems of missing groundtruth and the requirement of high efficiency when updating these visual prompts at test time, we introduce a local-global self-supervised learning strategy by enforcing the local and global consistency constraints on predictions. The local consistency constraints are conducted on intermediate and previously local fused results, enabling the model to be trained with high-quality pseudo groundtruth signals; the global consistency constraints are operated on sparse keyframes spanning long distances rather than per frame, allowing the model to learn from a consistent prediction over a long trajectory in an efficient way. Our experiments demonstrate that Online3R outperforms previous state-of-the-art methods on various benchmarks. Project page: https://shunkaizhou.github.io/online3r-1.0/