# AlignDiff: Learning Physically-Grounded Camera Alignment via Diffusion

arXiv: https://arxiv.org/abs/2503.21581 · HTML: https://mlsanity.com/paper/2503.21581/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 65 references that are in the map.
- First posted on arXiv 27 Mar 2025.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [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)
- [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)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception](https://mlsanity.com/paper/2306.06362/) (2023)
- [ControlNeXt: Powerful and Efficient Control for Image and Video Generation](https://mlsanity.com/paper/2408.06070/) (2024)
- [PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment](https://mlsanity.com/paper/2306.15667/) (2023)
- [Cameras as Rays: Pose Estimation via Ray Diffusion](https://mlsanity.com/paper/2402.14817/) (2024)
- [XFeat: Accelerated Features for Lightweight Image Matching](https://mlsanity.com/paper/2404.19174/) (2024)
- [DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation](https://mlsanity.com/paper/2307.01831/) (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)
- [DFNet: Enhance Absolute Pose Regression with Direct Feature Matching](https://mlsanity.com/paper/2204.00559/) (2022)
- [Perspective Fields for Single Image Camera Calibration](https://mlsanity.com/paper/2212.03239/) (2022)
- [FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent](https://mlsanity.com/paper/2404.15259/) (2024)
- [OmniGlue: Generalizable Feature Matching with Foundation Model Guidance](https://mlsanity.com/paper/2405.12979/) (2024)
- [Few-View Object Reconstruction with Unknown Categories and Camera Poses](https://mlsanity.com/paper/2212.04492/) (2022)
- [TIPS: Text-Image Pretraining with Spatial awareness](https://mlsanity.com/paper/2410.16512/) (2024)
- [Real-Time RGB-D Camera Pose Estimation in Novel Scenes using a Relocalisation Cascade](https://mlsanity.com/paper/1810.12163/) (2018)
- [Tame a Wild Camera: In-the-Wild Monocular Camera Calibration](https://mlsanity.com/paper/2306.10988/) (2023)
- [CTRL-C: Camera calibration TRansformer with Line-Classification](https://mlsanity.com/paper/2109.02259/) (2021)
- [A Closer Look at Self-Supervised Lightweight Vision Transformers](https://mlsanity.com/paper/2205.14443/) (2022)
- [Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints](https://mlsanity.com/paper/2007.15122/) (2020)
- [Blind Geometric Distortion Correction on Images Through Deep Learning](https://mlsanity.com/paper/1909.03459/) (2019)

## Built on by (most cited first, 2 of 2)

- [Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation](https://mlsanity.com/paper/2510.08673/) (2025)
- [Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States](https://mlsanity.com/paper/2609.04196/) (2026)

## Abstract (arXiv)

Accurate camera calibration is a fundamental task for 3D perception, especially when dealing with real-world, in-the-wild environments where complex optical distortions are common. Existing methods often rely on pre-rectified images or calibration patterns, which limits their applicability and flexibility. In this work, we introduce a novel framework that addresses these challenges by jointly modeling camera intrinsic and extrinsic parameters using a generic ray camera model. Unlike previous approaches, AlignDiff shifts focus from semantic to geometric features, enabling more accurate modeling of local distortions. We propose AlignDiff, a diffusion model conditioned on geometric priors, enabling the simultaneous estimation of camera distortions and scene geometry. To enhance distortion prediction, we incorporate edge-aware attention, focusing the model on geometric features around image edges, rather than semantic content. Furthermore, to enhance generalizability to real-world captures, we incorporate a large database of ray-traced lenses containing over three thousand samples. This database characterizes the distortion inherent in a diverse variety of lens forms. Our experiments demonstrate that the proposed method significantly reduces the angular error of estimated ray bundles by ~8.2 degrees and overall calibration accuracy, outperforming existing approaches on challenging, real-world datasets.