Depth-Dominant Skeleton Detection for Natural Scenes
2026-08-17 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors noticed that using only regular color images (RGB) makes detecting object skeletons in complicated pictures hard. They suggest using depth images, which show distance information and are less affected by color or texture, making it easier to find clear shapes. They created a new model called DDSkel that mainly uses depth images and adds a little RGB data to help. Despite being simpler and having fewer parameters than other top methods, their model performs better on a tough dataset with complex images.
skeleton detectionRGB imagesdepth imagesDDSkelasymmetric encoderSymPASCAL datasetmodality fusioncomputer visiontrainable parameters
Authors
Chengkun Rao, Yixuan Deng, Min Li, Yangjun Ou, Ye Li, Ziwei Luo, Zhaojing Wang, Junwei Tang, Bangchao Wang, Xiaoyun Yan
Abstract
To date, all natural scene skeleton detection follows the paradigm of taking RGB images as the sole input; despite notable progress, methods under this paradigm suffer significant performance degradation on complex-content images. We observe that depth images are inherently insensitive to color and texture, and can provide clear regional contours and inter-region spatial relationships, which naturally alleviates the difficulty of skeleton detection in complex scenarios. Motivated by this observation, this paper proposes for the first time a novel skeleton detection paradigm where depth images serve as the dominant modality and RGB images act as the auxiliary, and accordingly presents a model DDSkel (short for Depth-Dominant Skeleton Detection) under this paradigm. DDSkel employs an asymmetric encoder design to fuse RGB information into depth features, with the RGB modality branch having only 12% the parameters of the depth modality branch. DDSkel has a simple structure without intricate designs. Nevertheless, with only 36% of the trainable parameters of the current best method, DDSkel outperforms all state-of-the-art approaches on SymPASCAL, the most challenging dataset with a large volume of complex images.