PCBnet: A Dataset and Automatic Construction of SPICE Netlists from Schematic Images

Zhen Huang; Yuhao Gao; Yuzhi Liu; Daian Cheng; Chengyuan Shao; Yucheng Chen; Yongjian Jia; Futing Zhang

cs.CVAug 28, 2026

PCBnet: A Dataset and Automatic Construction of SPICE Netlists from Schematic Images

Authors: Zhen Huang, Yuhao Gao, Yuzhi Liu, Daian Cheng, Chengyuan Shao, Yucheng Chen, Yongjian Jia, Futing Zhang,

Organizations: Eastern Institute of Technology, Ningbo, China · University of Science and Technology of China, Hefei, China · Engineering Research Center of Chiplet Design and Manufacturing of Zhejiang Province · Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China ·

Abstract

Printed circuit boards (PCBs) are fundamental to modern electronic systems, yet AI-driven PCB design automation remains constrained by the lack of large-scale paired schematic-netlist datasets. PCB schematics are particularly challenging due to diverse component types, complex wiring topologies, and noisy textual annotations. To address this gap, we present PCBnet, a large-scale PCB schematic dataset comprising over 300 real-world designs with annotated pins and paired SPICE netlists. It contains more than 50,000 component instances, 150,000 wires, 100,000 text regions, and 400,000 characters. We further develop an automated schematic-to-netlist pipeline that combines visual recognition, topology construction, and domain-knowledge-guided multi-agent correction. The proposed method achieves 94.54% component detection mAP, 98.57% text recognition accuracy, and 84.47% end-to-end connectivity accuracy. PCBnet provides a benchmark and data foundation for future AI-driven PCB design automation.

Figures & tables

Fig. 1: Overview of PCBnet: the proposed pipeline reconstructs circuit netlists from PCB schematics through visual recognition, topology construction, and multi-agent correction.

Fig. 2: Overview of the schematic-to-netlist pipeline. Stage 1 extracts visual elements, including components, wires, and texts, from input PCB schematics. Stage 2 performs structure construction and element matching. Stage 3 applies a multi-agent correction framework, supported by a knowledge base via RAG, to correct and complete the final structured SPICE netlist.

Method	Comp. mAP	Wire. IoU	Conn. Acc.
Ours (PCBnet)	94.54	93.70	84.47
GPT-5.4	34.28	–	8.74
Claude Opus 4.6	29.63	–	7.91
Gemini 3 Pro	33.05	–	9.26
DeepSeek-V3.2	27.17	–	7.02
Qwen3.5-Plus	29.44	–	8.01

TABLE I: Comparison of component detection, wire extraction, and netlist construction accuracy.

Mode	Method	CER (%)	WER (%)	ACC (%)
Full Image	PaddleOCR	21.35	37.40	78.65
	EasyOCR	60.34	94.68	39.66
	Tesseract	22.34	42.16	77.66
	DocTR	22.99	50.00	77.01
	MMOCR	39.02	50.77	60.98
YOLO+	PaddleOCR	6.33	19.04	93.67

TABLE II: Comparison of OCR engines under full-image and detection-assisted settings.

Method	CER (%)	WER (%)	ACC (%)
YOLO+PaddleOCR	6.33	19.04	93.67
+ Knowledge-guided LLM	4.07	8.45	95.93
+ Multimodal Image Agent	2.52	4.67	97.48
+ Component Pairing	1.43	3.59	98.57

TABLE III: Ablation study of the multi-agent correction modules.

Electronic Design Automation

Electronic Design Automation uses algorithms and software to design, verify, optimize, and manufacture electronic circuits and systems.

See all 215 papers

SchGen: PCB Schematic Generation with Semantic-Grounded Code Representations
May 28, 2026Qinpei Luo, Ruichun Ma, Xinyu Zhang +1Electronic Design Automation LLM Code Generation
University of California, San Diego · Microsoft Research Asia · The University of Texas at Austin
SINA: A Fully Automated Circuit Schematic Image to Netlist Generator Using Artificial Intelligence
Jul 2, 2026Saoud Aldowaish, Yashwanth Karumanchi, Kai-Chen Chiang +4Electronic Design Automation Document Image Understanding
The Department of Electrical and Computer Engineering, University of Utah, Salt Lake City, UT, 48112 USA. · The Department of Electrical, Computer & Energy Engineering, University of Colorado Boulder, Boulder, CO 80309, USA.
pcbGPT: Automatic PCB Schematic Synthesis from Natural Language Requirements
May 31, 2026Tobias King, Steven Kehrberg, Michael Beigl +1Electronic Design Automation LLM-Based Program Synthesis
Karlsruhe Institute of Technology, Germany · Bosch Sensortec GmbH, Germany

May 28, 2026J/K move · Enter open · S save

SchGen: PCB Schematic Generation with Semantic-Grounded Code Representations

Qinpei Luo, Ruichun Ma, Xinyu Zhang, Lili Qiu

University of California, San Diego · Microsoft Research Asia · The University of Texas at Austin

Electronic Design Automation LLM Code Generation

Open paper AskPDF arXiv

Printed circuit board (PCB) schematic design defines nearly all electronic hardware, but it remains manual and expertise-intensive. While generative AI has advanced digital and analog IC design, PCB schematic generation from natural-language intent is largely unexplored. This paper presents SchGen, the first large language model that generates editable PCB schematics from natural-language requests. The key challenge lies in the lack of an LLM-suited representation and a large-scale dataset. Current schematic formats are dominated by verbose, tool-specific syntax and geometry-heavy descriptions, making them difficult to generate reliably. We introduce a semantically grounded code representation that encodes schematic editing primitives with relative placement and pin-name-based wiring, transforming a geometry-driven generation problem into a semantics-driven matching task amenable to LLMs. We further construct a large-scale dataset of PCB schematics paired with user prompts via a human-agent collaborative pipeline that converts open-source hardware designs into our representation. Experiments show that SchGen significantly outperforms alternative representations and even larger general-purpose LLMs on wire connectivity accuracy and functional correctness. Our results highlight the critical role of representation design in enabling generative models for complex hardware design tasks.

Abstract

Electronic Design Automation

Explore similar work

SchGen: PCB Schematic Generation with Semantic-Grounded Code Representations

SINA: A Fully Automated Circuit Schematic Image to Netlist Generator Using Artificial Intelligence

pcbGPT: Automatic PCB Schematic Synthesis from Natural Language Requirements