# Fast Soft Color Segmentation

arXiv: https://arxiv.org/abs/2004.08096 · HTML: https://mlsanity.com/paper/2004.08096/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2020.

## Built on by (most cited first, 13 of 13)

- [PaletteNeRF: Palette-based Appearance Editing of Neural Radiance Fields](https://mlsanity.com/paper/2212.10699/) (2022)
- [LayerD: Decomposing Raster Graphic Designs into Layers](https://mlsanity.com/paper/2509.25134/) (2025)
- [Deep Image Matting: A Comprehensive Survey](https://mlsanity.com/paper/2304.04672/) (2023)
- [Color Recommendation for Vector Graphic Documents based on Multi-Palette Representation](https://mlsanity.com/paper/2209.10820/) (2022)
- [CreatiParser: Generative Image Parsing of Raster Graphic Designs into Editable Layers](https://mlsanity.com/paper/2604.19632/) (2026)
- [AlphaVAE: Unified End-to-End RGBA Image Reconstruction and Generation with Alpha-Aware Representation Learning](https://mlsanity.com/paper/2507.09308/) (2025)
- [Multi-color balance for color constancy](https://mlsanity.com/paper/2105.10228/) (2021)
- [Ukiyo-e Analysis and Creativity with Attribute and Geometry Annotation](https://mlsanity.com/paper/2106.02267/) (2021)
- [Spatially varying white balancing for mixed and non-uniform illuminants](https://mlsanity.com/paper/2109.01350/) (2021)
- [Interactive Style Transfer: All is Your Palette](https://mlsanity.com/paper/2203.13470/) (2022)
- [Unsupervised Video Interpolation by Learning Multilayered 2.5D Motion Fields](https://mlsanity.com/paper/2204.09900/) (2022)
- [Workflow-Aware Structured Layer Decomposition for Illustration Production](https://mlsanity.com/paper/2603.14925/) (2026)
- [Learning to Synthesize Graphics Programs for Geometric Artworks](https://mlsanity.com/paper/2410.15768/) (2024)

## Abstract (arXiv)

We address the problem of soft color segmentation, defined as decomposing a given image into several RGBA layers, each containing only homogeneous color regions. The resulting layers from decomposition pave the way for applications that benefit from layer-based editing, such as recoloring and compositing of images and videos. The current state-of-the-art approach for this problem is hindered by slow processing time due to its iterative nature, and consequently does not scale to certain real-world scenarios. To address this issue, we propose a neural network based method for this task that decomposes a given image into multiple layers in a single forward pass. Furthermore, our method separately decomposes the color layers and the alpha channel layers. By leveraging a novel training objective, our method achieves proper assignment of colors amongst layers. As a consequence, our method achieve promising quality without existing issue of inference speed for iterative approaches. Our thorough experimental analysis shows that our method produces qualitative and quantitative results comparable to previous methods while achieving a 300,000x speed improvement. Finally, we utilize our proposed method on several applications, and demonstrate its speed advantage, especially in video editing.