Tessera

Drop a photo of a place: it finds where the photographer stood, the heading and the lens, then your group plans its own version in a shared 3D set.

Built with a teammate at HackUTD 2026; took 2nd place in the Spacetime track. Drop a photo of a place and Tessera finds where the photographer stood, which way they faced and which lens they used, in phone terms such as "2.2x on your iPhone". The solver matches the photo against a 3D model of the spot built from 155 Creative Commons photos: of 11 held-out photos it placed 10, 9 of them within 25 m of their GPS, with a median focal length error of 3%, and it says "Couldn't place" instead of guessing. The place then becomes a shared 3D set. Every person, prop, light and camera is a row in one SpacetimeDB module, so a drag on one screen shows on every other, and Nemotron places objects from a sentence. The group can plan from a browser, a phone or a Telegram chat. A LoRA fine-tune of Nemotron Nano 12B VL reads the lens of a photo. One spot, DUMBO in Brooklyn, is mapped exactly; anywhere else the place is marked approximate. The hosted demo ran until November 11, 2026; the video shows it and the code runs locally.

Ben Zhou

Ben Zhou giving a thumbs-up at his laptop at Cal Hacks 13.0
Ben at Cal Hacks 13.0, October 2026

Toronto

Ben Zhou

Third-year Computer Science and Finance/Economics student at the University of Toronto. Builds software, mostly at hackathons, and takes photographs.

Business card, to turn and flip

About

Education
University of Toronto, St. George
B.Sc. Computer Science and Finance/Economics, expected June 2028
Experience

Software Engineer, StealthMay 2026 to present · Toronto Launching soon.

Sponsorship Coordinator, Hack the ValleyMar 2026 to present · Toronto

Director of Technology, CUSEC (Canadian University Software Engineering Conference)Mar 2026 to present

Research and Development Manager, Rotman Commerce FinTech AssociationMar 2026 to present · Toronto

Marketing Manager, Rotman Commerce Venture Capital GroupMar 2026 to present · Toronto Designed and built rcventure.ca.

Research

Context-Based Captioning System, UofT Trustworthy Machine IntelligenceSept 2025 to Apr 2026 Fine-tuned Whisper for lecture speech recognition, producing real-time captions and corrected transcripts.

Hackathons

15 wins3 organized20+ attended

Photography
Shoots Sony: cities, water, cars, and the people in them. Took Photography 11 and 12 in high school, and made a short film (2023) and a music video (2024). See the photographs.
Languages
English and Mandarin Chinese (native), French (limited)
Tools
Python, TypeScript, JavaScript, Swift, Dart, Java, C++, SQL, Next.js, React, Node.js, Django, FastAPI, Flutter, Tailwind, PyTorch, Hugging Face, OpenCV, Git, GitHub, Docker, Postgres, Solana, Unity, Arduino, NVIDIA Jetson, ROS, SolidWorks, Fusion 360, Figma, Adobe Photoshop, DaVinci Resolve, Final Cut Pro

Projects