# Temporally Consistent Horizon Lines

arXiv: https://arxiv.org/abs/1907.10014 · HTML: https://mlsanity.com/paper/1907.10014/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2019.

## Built on by (most cited first, 8 of 8)

- [Spatial-Temporal Transformer for Dynamic Scene Graph Generation](https://mlsanity.com/paper/2107.12309/) (2021)
- [DepthCues: Evaluating Monocular Depth Perception in Large Vision Models](https://mlsanity.com/paper/2411.17385/) (2024)
- [Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images](https://mlsanity.com/paper/2105.02047/) (2021)
- [PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus](https://mlsanity.com/paper/2401.14919/) (2024)
- [SensorX2car: Sensors-to-car calibration for autonomous driving in road scenarios](https://mlsanity.com/paper/2301.07279/) (2023)
- [Robust Shape Fitting for 3D Scene Abstraction](https://mlsanity.com/paper/2403.10452/) (2024)
- [GimbalDiffusion: Gravity-Aware Camera Control for Video Generation](https://mlsanity.com/paper/2512.09112/) (2025)
- [Semantic Line Combination Detector](https://mlsanity.com/paper/2404.18399/) (2024)

## Abstract (arXiv)

The horizon line is an important geometric feature for many image processing and scene understanding tasks in computer vision. For instance, in navigation of autonomous vehicles or driver assistance, it can be used to improve 3D reconstruction as well as for semantic interpretation of dynamic environments. While both algorithms and datasets exist for single images, the problem of horizon line estimation from video sequences has not gained attention. In this paper, we show how convolutional neural networks are able to utilise the temporal consistency imposed by video sequences in order to increase the accuracy and reduce the variance of horizon line estimates. A novel CNN architecture with an improved residual convolutional LSTM is presented for temporally consistent horizon line estimation. We propose an adaptive loss function that ensures stable training as well as accurate results. Furthermore, we introduce an extension of the KITTI dataset which contains precise horizon line labels for 43699 images across 72 video sequences. A comprehensive evaluation shows that the proposed approach consistently achieves superior performance compared with existing methods.