# Projecting Points to Axes: Oriented Object Detection via Point-Axis Representation

arXiv: https://arxiv.org/abs/2407.08489 · HTML: https://mlsanity.com/paper/2407.08489/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 75 references that are in the map.
- First posted on arXiv 11 Jul 2024.

## Builds on (most cited first, 2 of 2)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Scene-Adaptive Attention Network for Crowd Counting](https://mlsanity.com/paper/2112.15509/) (2021)

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

- [Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models](https://mlsanity.com/paper/2408.10571/) (2024)
- [RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection](https://mlsanity.com/paper/2505.17732/) (2025)
- [Real-Time Oriented Object Detection Transformer in Remote Sensing Images](https://mlsanity.com/paper/2603.15497/) (2026)
- [RiO-DETR: DETR for Real-time Oriented Object Detection](https://mlsanity.com/paper/2603.09411/) (2026)
- [Set Prediction for Next-Day Active Fire Forecasting](https://mlsanity.com/paper/2605.10298/) (2026)
- [Explore Intrinsic Geometry for Query-based Tiny and Oriented Object Detector with Momentum-based Bipartite Matching](https://mlsanity.com/paper/2602.13728/) (2026)
- [Geometric Causal Models](https://mlsanity.com/paper/2607.05153/) (2026)
- [GTR: Gated Token Recurrence for Efficient Dense Prediction](https://mlsanity.com/paper/2609.26590/) (2026)

## Abstract (arXiv)

This paper introduces the point-axis representation for oriented object detection, emphasizing its flexibility and geometrically intuitive nature with two key components: points and axes. 1) Points delineate the spatial extent and contours of objects, providing detailed shape descriptions. 2) Axes define the primary directionalities of objects, providing essential orientation cues crucial for precise detection. The point-axis representation decouples location and rotation, addressing the loss discontinuity issues commonly encountered in traditional bounding box-based approaches. For effective optimization without introducing additional annotations, we propose the max-projection loss to supervise point set learning and the cross-axis loss for robust axis representation learning. Further, leveraging this representation, we present the Oriented DETR model, seamlessly integrating the DETR framework for precise point-axis prediction and end-to-end detection. Experimental results demonstrate significant performance improvements in oriented object detection tasks.