We build and train AI that truly understands the entire automotive insurance ecosystem — from every scratch and component to every claim, repair note, and document. Our models are designed to be ethical, transparent, and fair, helping make car insurance smarter for everyone.
MARS is a state-of-the-art deep learning model for car damage instance segmentation. It stands for:
By leveraging sequential quadtree attention, MARS refines segmentation masks at an instance level, surpassing existing methods (Mask R-CNN, PointRend, Mask Transfiner) with notable maskAP gains.
Presented at ICIAP 2023, Udine, Italy 🇮🇹
MARSAIL (Motor AI Recognition Solution Artificial Intelligence Laboratory) is dedicated to pioneering research at the intersection of computer vision, transformers, and automotive AI.
Our mission is to revolutionize the automotive insurance and repair industries through AI-driven automation, delivering breakthroughs in segmentation, localization, and decision intelligence.
MARS delivers superior segmentation accuracy:
MARSAIL drives the next generation of automotive AI and intelligent mobility through foundational transformer research led by Dr. Kao (Teerapong Panboonyuen). Our work unifies damage-centric computer vision, knowledge distillation at scale, and document intelligence into deployable systems—seamlessly translating cutting-edge research into production-ready impact for real-world automotive and insurance applications.
MARS introduced the Sequential Quadtree Attention mechanism, enabling precise instance-level damage mask refinement. This work demonstrated clear performance gains over Mask R-CNN, PointRend, and Mask Transfiner, and established the early research foundation of MARSAIL.
ALBERT is a large-scale transformer backbone for holistic vehicle damage understanding. It delivers rich contextual embeddings, multi-level localization, and robust attention signals—serving as a foundational teacher model for downstream automotive AI systems.
SLICK distills ALBERT’s knowledge into a lightweight, production-ready model. It delivers real-time, fine-grained damage segmentation optimized for insurance workflows and automated repair pipelines.
DOTA integrates deformable attention with retrieval-augmented generation to achieve human-level robustness in real-world automotive documents, including claims, invoices, and inspection reports.
git clone https://github.com/kaopanboonyuen/MARS.git cd MARS python3 -m venv mars-env source mars-env/bin/activate pip install -r requirements.txt
@inproceedings{panboonyuen2023mars,
title = {MARS: Mask Attention Refinement with Sequential Quadtree Nodes},
author = {Panboonyuen, Teerapong},
booktitle = {International Conference on Image Analysis and Processing (ICIAP)},
address = {Università degli Studi di Udine, Udine, Italy},
pages = {28--38},
year = {2023},
publisher = {Springer Nature Switzerland}
}
@article{panboonyuen2025albert,
title = {ALBERT: Advanced Localization and Bidirectional Encoder Representations from Transformers for Automotive Damage Evaluation},
author = {Panboonyuen, Teerapong},
journal = {arXiv preprint arXiv:2506.10524},
year = {2025}
}
@article{panboonyuen2025slick,
title = {SLICK: Selective Localization and Instance Calibration for Knowledge-Enhanced Car Damage Segmentation in Automotive Insurance},
author = {Panboonyuen, Teerapong},
journal = {arXiv preprint arXiv:2506.10528},
year = {2025}
}
@inproceedings{nithisopa2025dota,
title = {DOTA: Deformable Optimized Transformer Architecture for End-to-End Text Recognition with Retrieval-Augmented Generation},
author = {Nithisopa, Naphat and Panboonyuen, Teerapong},
booktitle = {2025 17th International Conference on Knowledge and Smart Technology (KST)},
pages = {301--306},
year = {2025},
organization = {IEEE}
}
Explore how our lab is shaping the future of automotive AI, blending deep vision models with smart insurance tech. Get the full story, insights, and breakthroughs from the MARSAIL team in our feature blog post.
Read the Full BlogThe official MARSAIL logo is available for use in academic papers, research posters, presentations, conference submissions, and other professional materials.
Please use the logo below when representing the laboratory in publications or collaborative work.
We build and train AI models using real-world car images and insurance data to support automated inspection, claims, and decision-making at scale.
Head of Laboratory · Senior Research Scientist
AI Data Engineer
AI Data Annotator
AI Data Annotator
AI Data Annotator
We are deeply grateful for the invaluable support of our sponsors, partners, and collaborators. Their investment and belief in our mission empower MARSAIL to push boundaries in automotive AI.
A special thank you to Thaivivat Insurance Public Company Limited (TVI) for their forward-thinking investment in AI-driven automotive solutions.
MARSAIL (MARS AI Lab)
Chulalongkorn University
PBY Artificial Intelligence Laboratory
MARSAIL is the dedicated Artificial Intelligence Laboratory under MARS (Motor AI Recognition Solution) . While MARS was founded earlier as a tech company, the AI-focused MARSAIL was later established and shaped by Dr. Teerapong Panboonyuen (Dr. Kao) , who leads the AI Research & Development division.
After completing his Ph.D. at Chulalongkorn University , Dr. Kao joined MARS in January 2022 to spearhead the next era of AI innovation. Upon reviewing the existing “first-generation AI system” from 2021, he made a decisive move — he removed the entire legacy system and rebuilt everything from the ground up.
This total reboot resulted in the new MARS model (Mask Attention Refinement with Sequential Quadtree Nodes), inspired partly by the company name. It became MARSAIL’s first official research publication and was presented on the international stage at ICIAP 2023 in Udine, Italy .
From 2022–2026, under Dr. Kao’s leadership, MARSAIL evolved into a next-generation AI research lab, producing advanced models including the flagship transformer ALBERT . Today, MARSAIL powers innovation across car insurance, damage analytics, intelligent document understanding, and AI assistance for vehicle damage assessment.
MARSAIL คือห้องปฏิบัติการปัญญาประดิษฐ์ของบริษัท MARS – Motor AI Recognition Solution (บริษัท มอเตอร์ เอไอ เรคอกนิชั่น โซลูชั่น จำกัด) โดยบริษัท MARS มีการก่อตั้งมาก่อน แต่ห้องแลป MARSAIL ถูกสร้างและพัฒนาโดย ดร.ธีรพงศ์ ปานบุญยืน (ดร.เก้า) ในฐานะ Head of AI Research เพื่อผลักดันการวิจัย AI ให้เติบโตระดับองค์กร
หลังจบ ปริญญาเอกจากจุฬาลงกรณ์มหาวิทยาลัย ดร.เก้าเริ่มเข้ามาทำงานที่ MARS ในช่วง มกราคม 2022 เพื่อสานต่องานพัฒนา AI จากทีมรุ่นแรกในปี 2021 แต่แทนที่จะปรับแต่งแบบเดิม เขากลับตัดสินใจครั้งใหญ่ — ลบระบบ AI เดิมทั้งหมด และสร้างระบบใหม่ตั้งแต่ศูนย์ เพื่อให้ทันสมัย แข็งแรง และรองรับงานระดับอุตสาหกรรม
โมเดลใหม่ที่เกิดจากการรีบูตนี้คือ MARS (Mask Attention Refinement with Sequential Quadtree Nodes) ซึ่งสอดคล้องกับชื่อบริษัท และได้เป็นงานวิจัยลำดับแรกของห้องแลป MARSAIL ที่ถูกนำเสนอในเวทีนานาชาติ ICIAP 2023 ณ ประเทศอิตาลี
ตั้งแต่ปี 2022–2026 ดร.เก้า ได้พัฒนา MARSAIL ให้เติบโตเป็นห้องวิจัย AI ระดับแนวหน้า สร้างโมเดลเด่น เช่น ALBERT ที่เป็นหัวใจของงานด้านประกันภัยรถยนต์ การประเมินรอยความเสียหาย การทำความเข้าใจเอกสารอัจฉริยะ และ AI assistance สำหรับงานประเมินราคาความเสียหายของรถยนต์ ผลักดันอุตสาหกรรมยานยนต์ไทยให้ล้ำหน้าด้วยพลังของ AI