# DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion

arXiv: https://arxiv.org/abs/2505.05473 · HTML: https://mlsanity.com/paper/2505.05473/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 33 of its 41 references that are in the map.
- First posted on arXiv 8 May 2025.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (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)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [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)
- [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)
- [BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks](https://mlsanity.com/paper/1911.10127/) (2019)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://mlsanity.com/paper/2305.08891/) (2023)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision](https://mlsanity.com/paper/2410.19115/) (2024)
- [Pixel-Perfect Structure-from-Motion with Featuremetric Refinement](https://mlsanity.com/paper/2108.08291/) (2021)
- [BA-Net: Dense Bundle Adjustment Network](https://mlsanity.com/paper/1806.04807/) (2018)
- [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)
- [RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild](https://mlsanity.com/paper/2208.05963/) (2022)
- [RelPose++: Recovering 6D Poses from Sparse-view Observations](https://mlsanity.com/paper/2305.04926/) (2023)
- [Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer](https://mlsanity.com/paper/2404.14351/) (2024)

## Built on by (most cited first, 14 of 14)

- [ViPE: Video Pose Engine for 3D Geometric Perception](https://mlsanity.com/paper/2508.10934/) (2025)
- [E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training](https://mlsanity.com/paper/2512.10950/) (2025)
- [MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion](https://mlsanity.com/paper/2507.23782/) (2025)
- [Video Generation Models are General-Purpose Vision Learners](https://mlsanity.com/paper/2607.09024/) (2026)
- [Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning](https://mlsanity.com/paper/2602.20157/) (2026)
- [E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models](https://mlsanity.com/paper/2506.01933/) (2025)
- [Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories](https://mlsanity.com/paper/2604.09429/) (2026)
- [Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment](https://mlsanity.com/paper/2512.08930/) (2025)
- [Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes](https://mlsanity.com/paper/2606.30047/) (2026)
- [Trajectory Densification and Depth from Perspective-based Blur](https://mlsanity.com/paper/2512.08627/) (2025)
- [Particle Diffusion Matching: Random Walk Correspondence Search for the Alignment of Standard and Ultra-Widefield Fundus Images](https://mlsanity.com/paper/2604.10085/) (2026)
- [Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images](https://mlsanity.com/paper/2605.07978/) (2026)
- [NaCR: Visual Localization via NeRF-aided Camera Ray Regression](https://mlsanity.com/paper/2609.25907/) (2026)
- [QuacamFM: Quaternion-Constrained Flow Matching for Camera Pose Estimation](https://mlsanity.com/paper/2609.32455/) (2026)

## Abstract (arXiv)

Current Structure-from-Motion (SfM) methods typically follow a two-stage pipeline, combining learned or geometric pairwise reasoning with a subsequent global optimization step. In contrast, we propose a data-driven multi-view reasoning approach that directly infers 3D scene geometry and camera poses from multi-view images. Our framework, DiffusionSfM, parameterizes scene geometry and cameras as pixel-wise ray origins and endpoints in a global frame and employs a transformer-based denoising diffusion model to predict them from multi-view inputs. To address practical challenges in training diffusion models with missing data and unbounded scene coordinates, we introduce specialized mechanisms that ensure robust learning. We empirically validate DiffusionSfM on both synthetic and real datasets, demonstrating that it outperforms classical and learning-based approaches while naturally modeling uncertainty.