# Depth-Dominant Skeleton Detection for Natural Scenes

arXiv: https://arxiv.org/abs/2608.16367 · HTML: https://mlsanity.com/paper/2608.16367/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Builds on (most cited first, 18 of 18)

- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects](https://mlsanity.com/paper/2407.16696/) (2024)
- [DeepSkeleton: Learning Multi-task Scale-associated Deep Side Outputs for Object Skeleton Extraction in Natural Images](https://mlsanity.com/paper/1609.03659/) (2016)
- [Multi-identity Human Image Animation with Structural Video Diffusion](https://mlsanity.com/paper/2504.04126/) (2025)
- [SRN: Side-output Residual Network for Object Symmetry Detection in the Wild](https://mlsanity.com/paper/1703.02243/) (2017)
- [DeepFlux for Skeletons in the Wild](https://mlsanity.com/paper/1811.12608/) (2018)
- [Object Skeleton Extraction in Natural Images by Fusing Scale-associated Deep Side Outputs](https://mlsanity.com/paper/1603.09446/) (2016)
- [Adaptive Linear Span Network for Object Skeleton Detection](https://mlsanity.com/paper/2011.03972/) (2020)
- [Linear Span Network for Object Skeleton Detection](https://mlsanity.com/paper/1807.09601/) (2018)
- [Hi-Fi: Hierarchical Feature Integration for Skeleton Detection](https://mlsanity.com/paper/1801.01849/) (2018)
- [WAS: Dataset and Methods for Artistic Text Segmentation](https://mlsanity.com/paper/2408.00106/) (2024)
- [ProMask: Probability Mask for Skeleton Detection](https://mlsanity.com/paper/2012.03003/) (2020)

## Abstract (arXiv)

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.