DA-Fusion: Deformable Attention-Based RGB-D Fusion Transformer for Unseen Object Instance Segmentation
2026-07-20 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors created a new method called DA-Fusion to help robots better recognize and separate objects they have never seen before, especially when objects are piled up or hiding parts of each other. Their method combines both color images (RGB) and depth information to get a clearer understanding of the objects. They also made a new dataset called OCBD to test how well this method works in typical warehouse picking scenarios. Tests show their method works better than previous ones for sorting and picking objects in cluttered settings.
instance segmentationRGB-D fusiondeformable attentiontransformerbin-pickingobject segmentationdepth sensinglogistics automationOCBD datasetrobotic perception
Authors
Yesol Park, Hye-Jung Yoon, Juno Kim, Byoung-Tak Zhang
Abstract
In logistics automation, precise segmentation of unseen objects is crucial for efficient robotic manipulation in cluttered environments. Tasks such as bin-picking and shelf-picking require robust perception to handle occlusions, varying object shapes, and complex spatial arrangements. Traditional RGB-based methods tend to over-segment objects due to their reliance on texture, while depth-based methods often under-segment by focusing primarily on geometric features. To address these limitations, we propose DA-Fusion, a deformable attention-based RGB-D fusion Transformer designed for unseen object instance segmentation. DA-Fusion effectively combines the strengths of both RGB and depth data, enhancing segmentation accuracy in cluttered and multi-layered object environments. We also introduce the Object Clutter Bin Dataset (OCBD), a benchmark dataset specifically tailored for evaluating bin-picking scenarios in top-down views. Extensive evaluations demonstrate that DA-Fusion outperforms state-of-the-art methods across diverse environments, making it particularly suited for real-world logistics tasks.