# PICASSO: A Feed-Forward Framework for Parametric Inference of CAD Sketches via Rendering Self-Supervision

arXiv: https://arxiv.org/abs/2407.13394 · HTML: https://mlsanity.com/paper/2407.13394/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 47 references that are in the map.
- First posted on arXiv 18 Jul 2024.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [A Neural Representation of Sketch Drawings](https://mlsanity.com/paper/1704.03477/) (2017)
- [Generalization in Generation: A closer look at Exposure Bias](https://mlsanity.com/paper/1910.00292/) (2019)
- [Im2Vec: Synthesizing Vector Graphics without Vector Supervision](https://mlsanity.com/paper/2102.02798/) (2021)
- [Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion](https://mlsanity.com/paper/2111.12702/) (2021)
- [Computer-Aided Design as Language](https://mlsanity.com/paper/2105.02769/) (2021)
- [Towards Layer-wise Image Vectorization](https://mlsanity.com/paper/2206.04655/) (2022)
- [SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design](https://mlsanity.com/paper/2007.08506/) (2020)
- [Learning to Paint With Model-based Deep Reinforcement Learning](https://mlsanity.com/paper/1903.04411/) (2019)
- [SketchGen: Generating Constrained CAD Sketches](https://mlsanity.com/paper/2106.02711/) (2021)
- [Vitruvion: A Generative Model of Parametric CAD Sketches](https://mlsanity.com/paper/2109.14124/) (2021)
- [CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention](https://mlsanity.com/paper/2402.17678/) (2024)
- [Deep Learning for Free-Hand Sketch: A Survey](https://mlsanity.com/paper/2001.02600/) (2020)
- [Inferring CAD Modeling Sequences Using Zone Graphs](https://mlsanity.com/paper/2104.03900/) (2021)
- [Engineering Sketch Generation for Computer-Aided Design](https://mlsanity.com/paper/2104.09621/) (2021)
- [CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations](https://mlsanity.com/paper/2208.10555/) (2022)
- [TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Clouds](https://mlsanity.com/paper/2407.12702/) (2024)
- [Neural Painters: A learned differentiable constraint for generating brushstroke paintings](https://mlsanity.com/paper/1904.08410/) (2019)
- [Deep Vectorization of Technical Drawings](https://mlsanity.com/paper/2003.05471/) (2020)
- [SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines](https://mlsanity.com/paper/2308.15966/) (2023)
- [Abstracting Sketches through Simple Primitives](https://mlsanity.com/paper/2207.13543/) (2022)
- [Discovering Design Concepts for CAD Sketches](https://mlsanity.com/paper/2210.14451/) (2022)
- [One Sketch for All: One-Shot Personalized Sketch Segmentation](https://mlsanity.com/paper/2112.10838/) (2021)

## Built on by (most cited first, 9 of 9)

- [CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers](https://mlsanity.com/paper/2412.13810/) (2024)
- [Text-to-CAD Evaluation with CADTests](https://mlsanity.com/paper/2605.07807/) (2026)
- [DAVINCI: A Single-Stage Architecture for Constrained CAD Sketch Inference](https://mlsanity.com/paper/2410.22857/) (2024)
- [How Effective is Pre-training of Large Masked Autoencoders for Downstream Earth Observation Tasks?](https://mlsanity.com/paper/2409.18536/) (2024)
- [MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scans](https://mlsanity.com/paper/2510.23429/) (2025)
- [PHT-CAD: Efficient CAD Parametric Primitive Analysis with Progressive Hierarchical Tuning](https://mlsanity.com/paper/2503.18147/) (2025)
- [Sketch2BIM: A Multi-Agent Human-AI Collaborative Pipeline to Convert Hand-Drawn Floor Plans to 3D BIM](https://mlsanity.com/paper/2510.20838/) (2025)
- [Reconstruction of a 3D wireframe from a single line drawing via generative depth estimation](https://mlsanity.com/paper/2604.13549/) (2026)
- [VisCAD: A Foundation Model Suite with Multimodal Industrial CAD Intelligence](https://mlsanity.com/paper/2609.03811/) (2026)

## Abstract (arXiv)

This work introduces PICASSO, a framework for the parameterization of 2D CAD sketches from hand-drawn and precise sketch images. PICASSO converts a given CAD sketch image into parametric primitives that can be seamlessly integrated into CAD software. Our framework leverages rendering self-supervision to enable the pre-training of a CAD sketch parameterization network using sketch renderings only, thereby eliminating the need for corresponding CAD parameterization. Thus, we significantly reduce reliance on parameter-level annotations, which are often unavailable, particularly for hand-drawn sketches. The two primary components of PICASSO are (1) a Sketch Parameterization Network (SPN) that predicts a series of parametric primitives from CAD sketch images, and (2) a Sketch Rendering Network (SRN) that renders parametric CAD sketches in a differentiable manner and facilitates the computation of a rendering (image-level) loss for self-supervision. We demonstrate that the proposed PICASSO can achieve reasonable performance even when finetuned with only a small number of parametric CAD sketches. Extensive evaluation on the widely used SketchGraphs and CAD as Language datasets validates the effectiveness of the proposed approach on zero- and few-shot learning scenarios.