# SEP-YOLO: Fourier-Domain Feature Representation for Transparent Object Instance Segmentation

arXiv: https://arxiv.org/abs/2603.02648 · HTML: https://mlsanity.com/paper/2603.02648/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Builds on (most cited first, 14 of 14)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [Concealed Object Detection](https://mlsanity.com/paper/2102.10274/) (2021)
- [Segmenting Transparent Objects in the Wild](https://mlsanity.com/paper/2003.13948/) (2020)
- [TransNeXt: Robust Foveal Visual Perception for Vision Transformers](https://mlsanity.com/paper/2311.17132/) (2023)
- [Learning to Upsample by Learning to Sample](https://mlsanity.com/paper/2308.15085/) (2023)
- [Enhanced Boundary Learning for Glass-like Object Segmentation](https://mlsanity.com/paper/2103.15734/) (2021)
- [Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World](https://mlsanity.com/paper/2107.03172/) (2021)
- [Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation](https://mlsanity.com/paper/2408.04804/) (2024)
- [Robotic Perception of Transparent Objects: A Review](https://mlsanity.com/paper/2304.00157/) (2023)
- [Glass Segmentation with RGB-Thermal Image Pairs](https://mlsanity.com/paper/2204.05453/) (2022)
- [Mamba YOLO: A Simple Baseline for Object Detection with State Space Model](https://mlsanity.com/paper/2406.05835/) (2024)
- [GLU Attention Improve Transformer](https://mlsanity.com/paper/2507.00022/) (2025)

## Abstract (arXiv)

Transparent object instance segmentation presents significant challenges in computer vision, due to the inherent properties of transparent objects, including boundary blur, low contrast, and high dependence on background context. Existing methods often fail as they depend on strong appearance cues and clear boundaries. To address these limitations, we propose SEP-YOLO, a novel framework that integrates a dual-domain collaborative mechanism for transparent object instance segmentation. Our method incorporates a Frequency Domain Detail Enhancement Module, which separates and enhances weak highfrequency boundary components via learnable complex weights. We further design a multi-scale spatial refinement stream, which consists of a Content-Aware Alignment Neck and a Multi-scale Gated Refinement Block, to ensure precise feature alignment and boundary localization in deep semantic features. We also provide high-quality instance-level annotations for the Trans10K dataset, filling the critical data gap in transparent object instance segmentation. Extensive experiments on the Trans10K and GVD datasets show that SEP-YOLO achieves state-of-the-art (SOTA) performance.