# Content Masked Loss: Human-Like Brush Stroke Planning in a Reinforcement Learning Painting Agent

arXiv: https://arxiv.org/abs/2012.10043 · HTML: https://mlsanity.com/paper/2012.10043/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2020.

## Built on by (most cited first, 15 of 15)

- [ProcessPainter: Learn Painting Process from Sequence Data](https://mlsanity.com/paper/2406.06062/) (2024)
- [StyleCLIPDraw: Coupling Content and Style in Text-to-Drawing Translation](https://mlsanity.com/paper/2202.12362/) (2022)
- [Toward Modeling Creative Processes for Algorithmic Painting](https://mlsanity.com/paper/2205.01605/) (2022)
- [Stroke-based Rendering: From Heuristics to Deep Learning](https://mlsanity.com/paper/2302.00595/) (2022)
- [Segmentation-Based Parametric Painting](https://mlsanity.com/paper/2311.14271/) (2023)
- [From Scratch to Sketch: Deep Decoupled Hierarchical Reinforcement Learning for Robotic Sketching Agent](https://mlsanity.com/paper/2208.04833/) (2022)
- [Interactive Neural Painting](https://mlsanity.com/paper/2307.16441/) (2023)
- [Collaborative Neural Painting](https://mlsanity.com/paper/2312.01800/) (2023)
- [CalliRewrite: Recovering Handwriting Behaviors from Calligraphy Images without Supervision](https://mlsanity.com/paper/2405.15776/) (2024)
- [Artificial Intelligence for Geometry-Based Feature Extraction, Analysis and Synthesis in Artistic Images: A Survey](https://mlsanity.com/paper/2412.01450/) (2024)
- [Character Generation through Self-Supervised Vectorization](https://mlsanity.com/paper/2208.02012/) (2022)
- [Robot Synesthesia: A Sound and Emotion Guided AI Painter](https://mlsanity.com/paper/2302.04850/) (2023)
- [DiffBMP: Differentiable Rendering with Bitmap Primitives](https://mlsanity.com/paper/2602.22625/) (2026)
- [Data-Efficient Brushstroke Generation with Diffusion Models for Oil Painting](https://mlsanity.com/paper/2603.01103/) (2026)
- [IMPASTO: Integrating Model-Based Planning with Learned Dynamics Models for Robotic Oil Painting Reproduction](https://mlsanity.com/paper/2603.29315/) (2026)

## Abstract (arXiv)

The objective of most Reinforcement Learning painting agents is to minimize the loss between a target image and the paint canvas. Human painter artistry emphasizes important features of the target image rather than simply reproducing it (DiPaola 2007). Using adversarial or L2 losses in the RL painting models, although its final output is generally a work of finesse, produces a stroke sequence that is vastly different from that which a human would produce since the model does not have knowledge about the abstract features in the target image. In order to increase the human-like planning of the model without the use of expensive human data, we introduce a new loss function for use with the model's reward function: Content Masked Loss. In the context of robot painting, Content Masked Loss employs an object detection model to extract features which are used to assign higher weight to regions of the canvas that a human would find important for recognizing content. The results, based on 332 human evaluators, show that the digital paintings produced by our Content Masked model show detectable subject matter earlier in the stroke sequence than existing methods without compromising on the quality of the final painting. Our code is available at https://github.com/pschaldenbrand/ContentMaskedLoss.