# CT-Bound: Robust Boundary Detection From Noisy Images Via Hybrid Convolution and Transformer Neural Networks

arXiv: https://arxiv.org/abs/2403.16494 · HTML: https://mlsanity.com/paper/2403.16494/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 36 references that are in the map.
- First posted on arXiv 25 Mar 2024.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection](https://mlsanity.com/paper/1909.01955/) (2019)
- [Learning to Parse Wireframes in Images of Man-Made Environments](https://mlsanity.com/paper/2007.07527/) (2020)
- [Learning Attraction Field Representation for Robust Line Segment Detection](https://mlsanity.com/paper/1812.02122/) (2018)
- [EDTER: Edge Detection with Transformer](https://mlsanity.com/paper/2203.08566/) (2022)
- [The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector](https://mlsanity.com/paper/2303.11828/) (2023)
- [Practical Edge Detection via Robust Collaborative Learning](https://mlsanity.com/paper/2308.14084/) (2023)
- [What Does a One-Bit Quanta Image Sensor Offer?](https://mlsanity.com/paper/2208.10350/) (2022)
- [Field of Junctions: Extracting Boundary Structure at Low SNR](https://mlsanity.com/paper/2011.13866/) (2020)
- [On Detection of Faint Edges in Noisy Images](https://mlsanity.com/paper/1706.07717/) (2017)
- [Fast Detection of Curved Edges at Low SNR](https://mlsanity.com/paper/1505.06600/) (2015)

## Built on by (most cited first, 3 of 3)

- [Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries](https://mlsanity.com/paper/2503.23606/) (2025)
- [Non-Learning Low-Light Stereo Vision](https://mlsanity.com/paper/2606.00379/) (2026)
- [Rate-optimal neural boundary detection from unlabeled noisy images](https://mlsanity.com/paper/2606.00715/) (2026)

## Abstract (arXiv)

We present CT-Bound, a robust and fast boundary detection method for very noisy images using a hybrid Convolution and Transformer neural network. The proposed architecture decomposes boundary estimation into two tasks: local detection and global regularization. During the local detection, the model uses a convolutional architecture to predict the boundary structure of each image patch in the form of a pre-defined local boundary representation, the field-of-junctions (FoJ). Then, it uses a feed-forward transformer architecture to globally refine the boundary structures of each patch to generate an edge map and a smoothed color map simultaneously. Our quantitative analysis shows that CT-Bound outperforms the previous best algorithms in edge detection on very noisy images. It also increases the edge detection accuracy of FoJ-based methods while having a 3-time speed improvement. Finally, we demonstrate that CT-Bound can produce boundary and color maps on real captured images without extra fine-tuning and real-time boundary map and color map videos at ten frames per second.