# Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation

arXiv: https://arxiv.org/abs/2006.00303 · HTML: https://mlsanity.com/paper/2006.00303/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2020.

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

- [LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2107.08623/) (2021)
- [Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection](https://mlsanity.com/paper/2107.12664/) (2021)
- [Arbitrary Shape Text Detection via Boundary Transformer](https://mlsanity.com/paper/2205.05320/) (2022)
- [GOSS: Towards Generalized Open-set Semantic Segmentation](https://mlsanity.com/paper/2203.12116/) (2022)
- [Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation](https://mlsanity.com/paper/2110.09734/) (2021)
- [Label-Free Cross-Task LoRA Merging with Null-Space Compression](https://mlsanity.com/paper/2603.26317/) (2026)
- [Learning to utilize image second-order derivative information for crisp edge detection](https://mlsanity.com/paper/2406.05779/) (2024)
- [Generalized Mask-aware IoU for Anchor Assignment for Real-time Instance Segmentation](https://mlsanity.com/paper/2312.17031/) (2023)

## Abstract (arXiv)

Image segmentation is a fundamental vision task and a crucial step for many applications. In this paper, we propose a fast image segmentation method based on a novel super boundary-to-pixel direction (super-BPD) and a customized segmentation algorithm with super-BPD. Precisely, we define BPD on each pixel as a two-dimensional unit vector pointing from its nearest boundary to the pixel. In the BPD, nearby pixels from different regions have opposite directions departing from each other, and adjacent pixels in the same region have directions pointing to the other or each other (i.e., around medial points). We make use of such property to partition an image into super-BPDs, which are novel informative superpixels with robust direction similarity for fast grouping into segmentation regions. Extensive experimental results on BSDS500 and Pascal Context demonstrate the accuracy and efficency of the proposed super-BPD in segmenting images. In practice, the proposed super-BPD achieves comparable or superior performance with MCG while running at ~25fps vs. 0.07fps. Super-BPD also exhibits a noteworthy transferability to unseen scenes. The code is publicly available at https://github.com/JianqiangWan/Super-BPD.