# UprightNet: Geometry-Aware Camera Orientation Estimation from Single Images

arXiv: https://arxiv.org/abs/1908.07070 · HTML: https://mlsanity.com/paper/1908.07070/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2019.

## Built on by (most cited first, 26 of 26)

- [Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction](https://mlsanity.com/paper/2103.12091/) (2021)
- [Perspective Fields for Single Image Camera Calibration](https://mlsanity.com/paper/2212.03239/) (2022)
- [GeoCalib: Learning Single-image Calibration with Geometric Optimization](https://mlsanity.com/paper/2409.06704/) (2024)
- [CTRL-C: Camera calibration TRansformer with Line-Classification](https://mlsanity.com/paper/2109.02259/) (2021)
- [Guided Co-Modulated GAN for 360deg Field of View Extrapolation](https://mlsanity.com/paper/2204.07286/) (2022)
- [Deep Learning for Camera Calibration and Beyond: A Survey](https://mlsanity.com/paper/2303.10559/) (2023)
- [Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning](https://mlsanity.com/paper/2109.10563/) (2021)
- [AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration](https://mlsanity.com/paper/2503.12701/) (2025)
- [Deepfake detection by exploiting surface anomalies: the SurFake approach](https://mlsanity.com/paper/2310.20621/) (2023)
- [Deep Rotation Correction without Angle Prior](https://mlsanity.com/paper/2207.03054/) (2022)
- [A Deep Perceptual Measure for Lens and Camera Calibration](https://mlsanity.com/paper/2208.12300/) (2022)
- [Neural Lens Modeling](https://mlsanity.com/paper/2304.04848/) (2023)
- [Rethinking Generic Camera Models for Deep Single Image Camera Calibration to Recover Rotation and Fisheye Distortion](https://mlsanity.com/paper/2111.12927/) (2021)
- [A Reliable Online Method for Joint Estimation of Focal Length and Camera Rotation](https://mlsanity.com/paper/2207.12934/) (2022)
- [Semi-Supervised Coupled Thin-Plate Spline Model for Rotation Correction and Beyond](https://mlsanity.com/paper/2401.13432/) (2024)
- [RotBench: Evaluating Multimodal Large Language Models on Identifying Image Rotation](https://mlsanity.com/paper/2508.13968/) (2025)
- [Floating No More: Object-Ground Reconstruction from a Single Image](https://mlsanity.com/paper/2407.18914/) (2024)
- [SOFI: Multi-Scale Deformable Transformer for Camera Calibration with Enhanced Line Queries](https://mlsanity.com/paper/2409.15553/) (2024)
- [Variational Structured Attention Networks for Deep Visual Representation Learning](https://mlsanity.com/paper/2103.03510/) (2021)
- [GimbalDiffusion: Gravity-Aware Camera Control for Video Generation](https://mlsanity.com/paper/2512.09112/) (2025)
- [CalibAnyView: Beyond Single-View Camera Calibration in the Wild](https://mlsanity.com/paper/2605.14615/) (2026)
- [G3T Up! Gravity Aligned Coordinate Frames Simplify Pointmap Processing](https://mlsanity.com/paper/2605.27372/) (2026)
- [A Simple Approach to Image Tilt Correction with Self-Attention MobileNet for Smartphones](https://mlsanity.com/paper/2111.00398/) (2021)
- [Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian](https://mlsanity.com/paper/2203.15235/) (2022)
- [Forecasting Solar Energy Using a Single Image](https://mlsanity.com/paper/2604.21982/) (2026)
- [Cross-View Yaw Estimation in Location Uncertainty with Line-Aligning Yaw Scoring](https://mlsanity.com/paper/2606.22094/) (2026)

## Abstract (arXiv)

We introduce UprightNet, a learning-based approach for estimating 2DoF camera orientation from a single RGB image of an indoor scene. Unlike recent methods that leverage deep learning to perform black-box regression from image to orientation parameters, we propose an end-to-end framework that incorporates explicit geometric reasoning. In particular, we design a network that predicts two representations of scene geometry, in both the local camera and global reference coordinate systems, and solves for the camera orientation as the rotation that best aligns these two predictions via a differentiable least squares module. This network can be trained end-to-end, and can be supervised with both ground truth camera poses and intermediate representations of surface geometry. We evaluate UprightNet on the single-image camera orientation task on synthetic and real datasets, and show significant improvements over prior state-of-the-art approaches.