# Light3R-SfM: Towards Feed-forward Structure-from-Motion

arXiv: https://arxiv.org/abs/2501.14914 · HTML: https://mlsanity.com/paper/2501.14914/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 61 references that are in the map.
- First posted on arXiv 24 Jan 2025.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [DSAC - Differentiable RANSAC for Camera Localization](https://mlsanity.com/paper/1611.05705/) (2016)
- [Visual Geometry Grounded Deep Structure From Motion](https://mlsanity.com/paper/2312.04563/) (2023)
- [Global Structure-from-Motion Revisited](https://mlsanity.com/paper/2407.20219/) (2024)
- [Pixel-Perfect Structure-from-Motion with Featuremetric Refinement](https://mlsanity.com/paper/2108.08291/) (2021)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow](https://mlsanity.com/paper/2211.10408/) (2022)
- [MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion](https://mlsanity.com/paper/2409.19152/) (2024)
- [PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment](https://mlsanity.com/paper/2306.15667/) (2023)
- [Patch2Pix: Epipolar-Guided Pixel-Level Correspondences](https://mlsanity.com/paper/2012.01909/) (2020)
- [Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses](https://mlsanity.com/paper/2305.14059/) (2023)
- [RelPose++: Recovering 6D Poses from Sparse-view Observations](https://mlsanity.com/paper/2305.04926/) (2023)

## Built on by (most cited first, 30 of 47)

- [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025)
- [ViPE: Video Pose Engine for 3D Geometric Perception](https://mlsanity.com/paper/2508.10934/) (2025)
- [Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey](https://mlsanity.com/paper/2507.14501/) (2025)
- [VGGT-Omega](https://mlsanity.com/paper/2605.15195/) (2026)
- [Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers](https://mlsanity.com/paper/2509.07120/) (2025)
- [SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization](https://mlsanity.com/paper/2508.17972/) (2025)
- [AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend](https://mlsanity.com/paper/2511.20343/) (2025)
- [VGG-T3: Offline Feed-Forward 3D Reconstruction at Scale](https://mlsanity.com/paper/2602.23361/) (2026)
- [Reconstructing 4D Spatial Intelligence: A Survey](https://mlsanity.com/paper/2507.21045/) (2025)
- [3R-GS: Best Practice in Optimizing Camera Poses Along with 3DGS](https://mlsanity.com/paper/2504.04294/) (2025)
- [LoMa: Local Feature Matching Revisited](https://mlsanity.com/paper/2604.04931/) (2026)
- [Alligat0R: Pre-Training Through Co-Visibility Segmentation for Relative Camera Pose Regression](https://mlsanity.com/paper/2503.07561/) (2025)
- [4D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimation](https://mlsanity.com/paper/2511.18416/) (2025)
- [Regist3R: Incremental Registration with Stereo Foundation Model](https://mlsanity.com/paper/2504.12356/) (2025)
- [MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation](https://mlsanity.com/paper/2601.06874/) (2026)
- [Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow](https://mlsanity.com/paper/2602.14021/) (2026)
- [E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models](https://mlsanity.com/paper/2506.01933/) (2025)
- [A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features](https://mlsanity.com/paper/2510.00978/) (2025)
- [UFO-4D: Unposed Feedforward 4D Reconstruction from Two Images](https://mlsanity.com/paper/2602.24290/) (2026)
- [Mem4D: Decoupling Static and Dynamic Memory for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2508.07908/) (2025)
- [MoRe: Monocular Geometry Refinement via Graph Optimization for Cross-View Consistency](https://mlsanity.com/paper/2510.07119/) (2025)
- [HuPrior3R: Incorporating Human Priors for Better 3D Dynamic Reconstruction from Monocular Videos](https://mlsanity.com/paper/2512.06368/) (2025)
- [Marginalized Bundle Adjustment: Multi-View Camera Pose from Monocular Depth Estimates](https://mlsanity.com/paper/2602.18906/) (2026)
- [Geometry-Guided Camera Motion Understanding in VideoLLMs](https://mlsanity.com/paper/2603.13119/) (2026)
- [LiDAR Prompted Spatio-Temporal Multi-View Stereo for Autonomous Driving](https://mlsanity.com/paper/2603.03765/) (2026)
- [Dark3R: Learning Structure from Motion in the Dark](https://mlsanity.com/paper/2603.05330/) (2026)
- [S-VGGT: Structure-Aware Subscene Decomposition for Scalable 3D Foundation Models](https://mlsanity.com/paper/2603.17625/) (2026)
- [SEAR: Simple and Efficient Adaptation of Visual Geometric Transformers for Unpaired RGB+Thermal 3D Reconstruction](https://mlsanity.com/paper/2603.18774/) (2026)
- [DeblurSplat: SfM-free 3D Gaussian Splatting with Event Camera for Robust Deblurring](https://mlsanity.com/paper/2509.18898/) (2025)
- [CuSfM: CUDA-Accelerated Structure-from-Motion](https://mlsanity.com/paper/2510.15271/) (2025)

## Abstract (arXiv)

We present Light3R-SfM, a feed-forward, end-to-end learnable framework for efficient large-scale Structure-from-Motion (SfM) from unconstrained image collections. Unlike existing SfM solutions that rely on costly matching and global optimization to achieve accurate 3D reconstructions, Light3R-SfM addresses this limitation through a novel latent global alignment module. This module replaces traditional global optimization with a learnable attention mechanism, effectively capturing multi-view constraints across images for robust and precise camera pose estimation. Light3R-SfM constructs a sparse scene graph via retrieval-score-guided shortest path tree to dramatically reduce memory usage and computational overhead compared to the naive approach. Extensive experiments demonstrate that Light3R-SfM achieves competitive accuracy while significantly reducing runtime, making it ideal for 3D reconstruction tasks in real-world applications with a runtime constraint. This work pioneers a data-driven, feed-forward SfM approach, paving the way toward scalable, accurate, and efficient 3D reconstruction in the wild.