Bolívar Enrique Solarte Pardo Ai / ML Researcher

I’m an Ai and Machine Learning Researcher at ITRI (Industrial Technology Research Institute) in Hsinchu, Taiwan 🇹🇼. With over six years of research and engineering experience, I’ve worked on various projects in computer vision, image processing, machine learning, and robotics, leading to top-tier publications and successful robot industrial applications.

Originally from Ecuador 🇪🇨, I moved to Taiwan in 2017 to pursue my studies and career. I received my M.S. degree in Electrical and Electronic Engineering in 2019 under the supervision of Prof. Syh-Shiuh Yeh at National Taipei University of Technology, where my research aimed at estimating cutting insert parameters for CNC machines using Genetic Algorithms and Artificial Neural Networks.

In 2024, I received my Ph.D. degree from National Tsing Hua University under the supervision of Prof. Sun Min, in collaboration with Prof. Wei-Chen Chiu and Dr. Yi-Hsuan Tsai, where my research focused on geometric perception, particularly self-training solutions using 360° cameras and multi-view consistency.

In general, my research interests lie in geometry perception and robotics. More specifically, I am fascinated by cognitive perception and scene understanding, from the perspectives of neuroscience and robotics. Eager to learn, I am always open to new ideas and collaborations!

enrique.solarte.pardo [at] gmail.com.

Education

National Tsing Hua University
Ph.D. in Electrical and Electronic Engineering
2019-2024
GPA: 3.1/4.0
National Taipei University of Technology
Master in Science, Electrical and Electronic Engineering
2017-2019
GPA: 3.5/4.0
The University of the Armed Forces, ESPE
Bachelor, Mechatronics Engineering
2008-2014
Grade: 17/20

Publications

iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Views
Chin-Hsuan Wu, Yen-Chun Chen, Bolivar Solarte , Yen-Chun Chen, Min Sun
3DV 2024
icons/website.svg [Project Page] icons/paper.svg [ArXiv] icons/github.svg [Code]
uLayout: Unified Room Layout Estimation for Perspective and Panoramic Images
Jonathan Lee, Bolivar Solarte , Chin-Hsuan Wu, Jin-Cheng Jhang, Yi-Hsuan Tsai, and Min Sun.
WACV 2024
icons/soon.svg [coming soon...]
Self-training Room Layout Estimation via Geometry-aware Ray-casting
Bolivar Solarte , Chin-Hsuan Wu, Jin-Cheng Jhang, Jonathan Lee, Yi-Hsuan Tsai, and Min Sun.
ECCV 2024
icons/website.svg [Project Page] icons/paper.svg [ArXiv] icons/github.svg [Code] icons/dataset.svg [Dataset]
360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning
Bolivar Solarte , Chin-Hsuan Wu, Yueh-Cheng Liu, Yi-Hsuan Tsai, Min Sun
NeurIPS 2022
icons/website.svg [Project Page] icons/paper.svg [ArXiv] icons/github.svg [Code] icons/dataset.svg [Dataset]
360-DFPE: Leveraging Monocular 360-Layouts for Direct Floor Plan Estimation
Bolivar Solarte , Yueh-Cheng Liu, Chin-Hsuan Wu, Yi-Hsuan Tsai, Min Sun
IEEE Robotics and Automation Letters (RA-L) 2022
icons/website.svg [Project Page] icons/paper.svg [ArXiv] icons/github.svg [Code] icons/dataset.svg [Dataset]
Robust 360-8PA: Redesigning The Normalized 8-point Algorithm for 360-FoV Images
Bolivar Solarte , Chin-Hsuan Wu, Kuan-Wei Lu, Yi-Hsuan Tsai, Wei-Chen Chiu, Min Sun.
ICRA 2021
icons/website.svg [Project Page] icons/paper.svg [ArXiv] icons/github.svg [Code] icons/dataset.svg [Dataset]
360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume
Ning-Hsu Wang, Bolivar Solarte , Yi-Hsuan Tsai, Wei-Chen Chiu, Min Sun
ICRA 2020
icons/website.svg [Project Page] icons/paper.svg [ArXiv] icons/github.svg [Code]
Cutting Insert and Parameter Optimization for Turning Based on Artificial Neural Networks and a Genetic Algorithm
Bolivar Solarte , Diego Hidalgo, Syh-Shiuh Yeh.
Applied Sciences 2019
icons/paper.svg [Paper]

Projects

Semantic Map and Robot Reasoning
ITRI - Industrial Technology Research Institute - 2024
This project focused on building a semantic map for robot reasoning and scene understanding. In general, the developed system identifies meaningful objects and their features embedding representation aligned with natural language, using VLM and LLM models. This enabled the robot to understand actions through natural language instructions while also interpreting geometric relationships and contextual information. The system was implemented in Python and ROS2 and was evaluated in both Nvidia Isaac Simulation and real-world scenarios.
iClerk: Using LLM for product dispatching
ITRI - Industrial Technology Research Institute - 2024
In this project, we developed a clerk robot system that utilizes VLM and LLM models to understand natural language instructions and autonomously dispatch products. The system can recognize implicit information, interpret contextual requirements, and seamlessly add new products without constraints. It was implemented in Python and ROS1 and was presented at TAIROS 2024 in Taipei, Taiwan.
icons/newspaper.svg [Blog] icons/youtube.svg [Video]
Vision Inspection System
ITRI - Industrial Technology Research Institute - 2024
This project focused on a vision inspection system to verify the correct positioning of a workpiece before the CMM machine began its inspection. It used an RGB camera and relied solely on image processing for the task, without a deep neural network. The system was implemented in Python and ROS and achieved a precision of ±0.5 mm and a recall of over 99%. The system was evaluated in a real-world scenario.
MVL Challenge: Multi-View Layout Estimation
Workshop on Omnidirectional Computer Vision - CVPR 2023
This was the first challenge on self-training multi-view layout estimation, where the goal was to explore solutions that rely solely on multi-view information to estimate scene layouts (without human annotations). The challenge was part of the Workshop on Omnidirectional Computer Vision, held in CVPR 2023.
icons/website.svg [Project Page] icons/dataset.svg [Dataset] icons/paper.svg [Presentation]
Autonomous Vision Inspection System
ITRI - Industrial Technology Research Institute - 2023
This project aimed to develop an autonomous inspection system for a manufacturing process with over 100 production stations. The deployed robot used a classical LiDAR-based SLAM algorithm for localization and a inspection system that incorporated an auto-labeled object detector, a Structure-from-Motion map for each station, and a multi-infrared-camera rig. It achieved a precision of ±5 mm and a recall of over 98%. The system was implemented in C++, Python, and ROS.
Stereo VSLAM for an AVG robot
MIRLE Automation Corporation - 2022
This project aimed to validate a vision-based system as a reliable alternative to a LiDAR-based approach for an AGV robot. It was built upon open-source VSLAM algorithms with modifications, including a scale recovery system, self-calibration, and custom sensor fusion. Tested on a real robot, the system achieved an error margin within 5 cm. It was implemented in C++ and Python.
Robot Mobile Platform for Patrolling Convenience Stores
ITRI - Industrial Technology Research Institute - 2018
In this project, I was responsible for the perception module of an autonomous mobile platform patrolling convenience stores. My main task was to develop an object detection system trained on custom products. The system ran on the robot’s onboard hardware at around 20 FPS without a GPU. It was implemented using Python, C++, and ROS. This robot was presented in TAIROS 2018, in Taipei, Taiwan.
Servo Control Tuning Using Genetic Algorithms and Gradient Descent
ITRI - Industrial Technology Research Institute - 2017
This project aimed to optimize and fine tune the control parameters of a servo control system under unknown external conditions. Due to the high non-linearity of the parameters space, we used a Genetic Algorithm to find the most promising region space, and then used a Gradient Descent algorithm to fine the final model. The project was developed in C# and Matlab.
icons/paper.svg [Recommendation Letter]