用深度图主导的骨架检测，让复杂场景识别更准。
Depth-Dominant Skeleton Detection for Natural Scenes
- 以深度图为主输入，RGB为辅，融合更高效
- 参数仅36%却超越当前最优方法
- 适合复杂纹理场景，结构简单易部署
目前自然场景骨架检测均以RGB图像为唯一输入，尽管取得进展，但在内容复杂的图像上性能显著下降。我们发现深度图对颜色和纹理不敏感，能清晰呈现区域轮廓与空间关系，天然缓解复杂场景下的检测难度。受此启发，本文首次提出以深度图为主导模态、RGB为辅助的新型骨架检测范式，并设计了相应模型DDSkel（Depth-Dominant Skeleton Detection）。DDSkel采用非对称编码器结构，将RGB信息融入深度特征，其中RGB分支参数仅为深度分支的12%。模型结构简洁，无复杂设计。尽管训练参数仅占当前最优方法的36%，在包含大量复杂图像的最挑战数据集SymPASCAL上仍全面超越所有先进方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。