News

WWNYTV7

Clarkson’s Fix-It Technology Jul 2022

Publications

This thesis describes six approaches to repair broken objects and two large-scale datasets enabling the repair of broken objects.
Talk
CVPR2023

We present Fantastic Breaks (and Where to Find Them), a dataset containing scanned, waterproofed, and cleaned 3D meshes for 150 broken objects, paired and geometrically aligned with complete counterparts.
Dataset Project DOI arXiv
arXiv

We present Pix2Repair, an automated shape repair approach that generates restoration shapes from images to repair fractured objects.
Code DOI arXiv
ICARA2023

We present an approach using reinforcement learning that combines visual and tactile information to automatically assemble repair parts to fractured objects.
PDF DOI
ARSO2023

We present a large-scale study of human-human handover behavior involving 96 participant dyads derived from 32 participants in total and 204 objects.
PDF DOI
SIGGRAPH Asia 2022

We introduce DeepJoin, an automated approach to generate high-resolution repairs for fractured shapes using deep neural networks.
PDF Code Dataset Video DOI arXiv
ECCV2022

We present DeepMend, a novel approach to reconstruct restorations to fractured shapes using learned occupancy functions.
PDF Code Poster Video DOI arXiv
SGP2022

We provide a novel approach to perform fully automated generation of restorations for fractured shapes using learned implicit shape representations in the form of occupancy functions.
PDF Code Video Talk DOI
SCF2021

We present an approach that takes a 3D model of a broken object and retrieves proxy 3D models of corresponding complete objects from a library of 3D models, with the goal of using the complete proxy to repair the broken object.
PDF Code Project DOI
SCF2019

We provide an approach to automatically reconstruct a 3D printed restoration piece for a broken object from 3D scanned meshes of the broken object and an original counterpart.
PDF Talk DOI
BigData2018

We present a low-cost strawberry detection system based on convolutional neural networks to improve the efficiency of typical agricultural operations.
PDF Dataset DOI
MMM2018

We present a microenvironment of multiple cameras to capture multi-viewpoint time-lapse videos of objects showing spatiotemporal phenomena such as aging.
PDF Video DOI
MMM2018

We create a novel 3D scanning system using consumer grade hardware that revolves a camera around the object of interest, does not disturb the object during capture and allows us to scan delicate objects that can deform under motion.
PDF Video DOI
MMM2018

We provide an approach to reconstruct spatiotemporal 3D models of aging objects such as fruit containing time-varying shape and appearance using multi-view time-lapse videos captured by a microenvironment of Raspberry Pi cameras.
PDF DOI

Experience

 
 
 
 
 

Research Intern

Delsys

May 2023 – Oct 2023 Natick, Massachusetts
Mentored by Bhawna Shiwani and Dr. Joshua Kline.
Research Responsibilities:
Led computer vision team to realize DIU and DOD projects, composed quarterly reports and grant proposals, mentored incoming research associates.
 
 
 
 
 

NSF GRFP Graduate Research Assistant

Clarkson University

Jan 2021 – May 2024 Potsdam, New York
Mentored by Dr. Natasha Banerjee (CS).
Thesis: Project to automate the repair of broken or damaged objects.
 
 
 
 
 

Engineering Intern

Qualcomm

May 2019 – Aug 2019 San Diego, California
Research Projects:
* Quantized and optimized existing neural networks for deployment on state-of-the-art Qualcomm handset devices.
* Developed a software API in Python to convert neural networks to a proprietary format and execute them on Qualcomm handset devices.
 
 
 
 
 

Makerspace Supervisor

Clarkson University

Jul 2018 – May 2019 Potsdam, New York
Responsibilities:
* Guided purchasing of approximately $50,000 worth of equipment for on-campus Makerspace, and assembled and maintained this equipment.
* Interviewed, trained, and managed eight student staff for University Makerspace.
* Worked with interns to structure and staff events including Business Plan Competition, President’s Challenge Kickoff, and President’s Challenge Workshop Series.
 
 
 
 
 

Undergraduate Researcher

Lehigh University

May 2018 – Jul 2018 Bethlehem, Pennsylvania
Mentored by: Dr. Mooi Choo Chuah (CS).
Research Projects:
* Trained neural network to detect strawberries in Python that achieves 84.2% accuracy at 1.63FPS and can be deployed for under $50.
* Collaboratively developed a Python API for a robot arm to automatically pick strawberries using my neural network.
 
 
 
 
 

Undergraduate Researcher

Clarkson University

Jan 2017 – May 2019 Potsdam, New York
Mentored by Dr. Sean Banerjee (CS) and Dr. Natasha Banerjee (CS).
Research Projects:
* Developed and published an algorithm to automatically produce smoothly-joining 3D-printable restoration parts for broken objects.
* Developed and published a photogrammetry based 3D scanner, which is parametric, modular, and can be 3D printed at low cost.
* Managed research group in synthesizing 957 high point density 3D models using my 3D scanner to verify proposed scanning optimizations.
* Created parametric platonic solid calibration targets in OpenSCAD to enable quicker calibration of multi-camera systems.
Responsibilities:
* Mentored four undergraduate students in hardware prototyping and computational fabrication.

Accomplish­ments

NSF Graduate Research Fellow

National Science Foundation May 2019

Grand Prize Winner, Clarkson President’s Challenge

Clarkson University May 2019

College of Arts and Sciences Award

Clarkson University Apr 2019

Hamlin/Darraugh Award for Computer Science

Clarkson University Apr 2019

R. Gerald Bradshaw Award for Computer Science

Clarkson University Apr 2018

Best Presentation, Clarkson Research and Project Showcase

Clarkson University Apr 2017

Contact

  • lambne at clarkson dot edu