Deep Image Orientation Angle Detection
Not on the map. Why?
Abstract (arXiv)
Estimating and rectifying the orientation angle of any image is a pretty challenging task. Initial work used the hand engineering features for this purpose, where after the invention of deep learning using convolution-based neural network showed significant improvement in this problem. However, this paper shows that the combination of CNN and a custom loss function specially designed for angles lead to a state-of-the-art results. This includes the estimation of the orientation angle of any image or document at any degree (0 to 360 degree),
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Jun 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 0; 2023: 0; 2024: 1; 2025: 1; 2026: 2.
5 papers.
- 2025BitMark: Watermarking Bitwise Autoregressive Image Generative Modelscited by 5
- 2021A Simple Approach to Image Tilt Correction with Self-Attention MobileNet for Smartphonescited by 1
- 2026Depth-Aware Image and Video Orientation Estimationcited by 1
- 2024Silver medal Solution for Image Matching Challenge 2024cited by 0
- 2026Image Rotation Angle Estimation: Comparing Circular-Aware Methodscited by 0
- 2026Depth-Aware Image and Video Orientation Estimation15 Apr 2026
- 2026Image Rotation Angle Estimation: Comparing Circular-Aware Methods26 Mar 2026
- 2025BitMark: Watermarking Bitwise Autoregressive Image Generative Models26 Jun 2025
- 2024Silver medal Solution for Image Matching Challenge 20244 Nov 2024
- 2021A Simple Approach to Image Tilt Correction with Self-Attention MobileNet for Smartphones31 Oct 2021