Jerrin Bright

I am a Founding Engineer at Mecka AI, building the data and deployment layer for robotics. My work spans egocentric perception, dense video understanding, multimodal model development, and scalable pretraining, post-training, and data pipelines for VLA and world-model systems. I am also a doctoral candidate at the University of Waterloo, supervised by Dr. John Zelek.

My work focuses on visual understanding from sparse, real-world video. At Mecka, I build video-understanding and multimodal-learning systems for egocentric embodied agents. In my PhD, I study 4D human-scene reconstruction from monocular videos using 3D foundation models. My earlier work in sports biomechanics focused on practical motion analysis from ordinary baseball and softball video.

Previously, I collaborated with the Baltimore Orioles (MLB) for 3+ years on markerless player kinematics and pitch analysis from video, supporting biomechanics-driven performance evaluation.

Email  /  CV  /  Scholar  /  X  /  LinkedIn

profile photo

News

  • [2026/09] 🎉 WildHSR is submitted to ICLR 2027! [Project Page]
  • [2026/07] 🎉 Awarded the Merit Scholarship Award at the University of Waterloo!
  • [2026/06] 🎉 CoGS is submitted to 3DV 2027! [Project Page] [arXiv]
  • [2026/06] Attended CVPR 2026 in Denver, Colorado.
  • [2026/05] 🚀 DraftPilot is released, a local-first AI workspace for research papers! [Website]
  • [2026/05] 🎉 DreamPose3D gets accepted to IEEE Transactions on Multimedia! [Early Access]
  • [2026/04] Advanced to PhD candidacy at the University of Waterloo.
  • [2026/03] 🎉 Three papers get accepted to CVPR Workshop 2026!
  • [2025/12] Attended NeurIPS 2025 in San Diego.
  • [2025/09] Joined Mecka AI as Founding Engineer.
  • [2025/08] On-site with Baltimore Orioles for PitcherNet deployment.
  • [2025/05] 🎉 Gen4D gets accepted to CVPR Workshop 2025.
  • [2025/05] 🎉 SportMamba gets accepted as Oral at CVPR Workshop 2025!
  • [2025/04] Featured in media for PitcherNet.
  • [2024/09] 🎉 TokenCliPose gets accepted to NeurIPS 2024!
  • [2024/05] 🏆 Best Paper Award at CRV 2024!
  • [2024/04] 🎉 PitcherNet gets accepted as Oral at CVPR Workshop 2024!

Timeline
Aug 2025 - Present
Mecka AI
Egocentric Perception, Video Understanding, Embodied Agents
Sep 2022 - Apr 2026
Waterloo × Orioles
World Reconstruction, Sports Vision, Neural Rendering
Jul 2021 - Apr 2022
IISc
UAV Navigation, Multimodal Learning, Event Detection
Jul 2021 - Sep 2021
McMaster
Soft Robotics, Modeling & Analysis, Simulation
May 2021 - Jul 2021
Arizona State
Photogrammetry, 3D Reconstruction, Sensor Fusion
Oct 2020 - Apr 2021
Aero2Astro
Visual Odometry, GPS-Denied Navigation, VI-SLAM
Apr 2020 - Jun 2020
Yuan-Ze
Localization, Conditional Fields, Anomaly Detection

Things I Built

DraftPilot
Local-first AI workspace for writing LaTeX research papers with local PDF compilation, SyncTeX navigation, linked codebase context, todo planning, and deadline management.
Website | Discord
OpenForm Labs
Private beta for teams, coaches, and player development groups, turning ordinary baseball and softball video into accessible 3D biomechanics insights and shareable athlete reports.

Research

I aim to build systems that understand people, motion, and interactions in the physical world from everyday video. Currently, my work focuses on three directions:

  • Building large foundation models for dense labeling of egocentric video for embodied AI.
  • Reconstructing dynamic humans, objects, and scenes from monocular video.
  • Recovering 3D human motion from sports video for biomechanical analysis.

Full publication list on Google Scholar.

Thesis
PhD Comprehensive Exam
4D World Reconstruction of Humans, Scenes, and Camera Systems
Supervisor: John Zelek
PhD Comprehensive Exam, University of Waterloo, 2026 · GPA: 4.0/4.0
Slides | BibTeX
thesis
Robust 3D Human Modeling for Baseball Sports Analytics
Supervisor: John Zelek
Master's Thesis, University of Waterloo, 2024 · GPA: 3.9/4.0
UWSpace | Slides | BibTeX
thesis
End-to-End Autonomous UAV System in GPS-Denied and Unstructured Environments
Supervisor: Arockia Selvakumar
Bachelor's Thesis, VIT Chennai, 2022 · GPA: 3.7/4.0
PDF | Slides | BibTeX

Selected Awards

  • 2026:Merit Scholarship Award, University of Waterloo
  • 2026:Graduate Student Research Dissemination Award, University of Waterloo
  • 2025:International Doctoral Student Award, University of Waterloo
  • 2025:Engineering Graduate Merit Award, University of Waterloo
  • 2025:University of Waterloo Graduate Scholarship, University of Waterloo
  • 2024:Best Paper Award (Computer Vision), Conference on Robots and Vision
  • 2024:MITACS Accelerate International Award, University of Waterloo
  • 2024:International Master's Award of Excellence, University of Waterloo
  • 2024:Graduate Research Studentship, University of Waterloo
  • 2022:MITACS Globalink Graduate Fellowship, MITACS Canada
  • 2022:Best Outgoing Student - Robotics Club, Vellore Institute of Technology, Chennai, India
  • 2021:MITACS Graduate Research Fellowship, University of Waterloo
  • 2020:Outstanding Paper Award, RIACT International Conference

Academic Service

Reviewer: CVPR, ICLR, BMVC, NeurIPS, 3DV, IROS, EAAI, CVSports, CVIU, MMSports, TNNLS, TCSVT, TMM, CVIS, CTIS, IMAVIS, The Journal of Supercomputing

Technical Program Member: ACM MMSports @ ACM Multimedia 2024

Teaching Assistant:

  • SYDE461: Systems Design Capstone Project 1 (Fall 2023, Fall 2024)
  • SYDE462: Systems Design Capstone Project 2 (Winter 2024, Winter 2025)
  • SYDE361: Systems Design Methods 1: Needs Analysis and Prototyping (Summer 2024)
  • BME361: Biomedical Engineering Design (Winter 2023)
  • BME101L: Communications in Biomedical Engineering: Visualization (Fall 2022)

Media Coverage

My work has been featured in:

  • Toronto Star: "The Baltimore Orioles are developing a game-changing baseball technology, with help from a Canadian university" (April 18, 2025)
  • Baltimore Sun: "Orioles developing form of AI technology that could someday change scouting forever" (April 23, 2025)
  • UWaterloo Media: "PitcherNet helps researchers throw strikes with AI analysis" (April 23, 2025)
  • CTV News: "Making a pitch to change the game: Waterloo tech to analyze baseball pitcher's performance with smartphone" (April 29, 2025)
  • CBC News: "UW researchers use AI to analyze baseball players' movements" (April 30, 2025)
  • The Globe and Mail: "University of Waterloo, Orioles partner on AI project to track pitcher biomechanics" (April 29, 2025)
  • Global News: "University of Waterloo researchers develop AI technology for Baltimore Orioles" (May 13, 2025)
  • Baseball HQ Radio: "Friday Full Edition w Jerrin Bright" (May 23, 2025)

Designed based on Jon Barron's website. Last updated: October 16, 2026.