sheesdev

I've published two papers on using HE for ML and it's nice, but also alarming, to see big players like Google and Microsoft making decent tools for performing HE. Although the technology is still much farther out from being commercially viable, it does pose an interesting problem about how these data aggregation companies will utilise a tech that is inherently private.

The mouse render is surprisingly good. Several of those clips stood out to be a pretty big leap in terms of current SOTA models.

The only one that looks "off" is the beverage ad video during the can opening clip, it still has that "AI smoothening" effect. Good thing this can be done pretty well using traditional rendering.

I feel like for a good while now we'll transition into a process that uses traditional "close-up" rendering/shots + AI generated wide-shots or quick cuts.

Exciting, but also troubling. This being open-weights is a massive win for the community though.

Thank you so much!

I want to write a Blog about the entire technical and creative aspect of designing and developing it as well as all the challenges that I faced, what worked vs what didn't, what I spent months on, only to get scrapped etc. Would HN be interested in reading it?

This sounds really interesting and something I'd love to try. Do you have more details on how someone else can utilise this?

Location: Bhopal, India

Remote: Yes

Willing to relocate: Yes

Portfolio: https://shees.dev

Technologies: C++, Python, Blender, Three.js, WebGL/GLSL, OpenGL, PyTorch, 3D Graphics, Java,

Spring Boot, PostgreSQL, React, Git

Résumé/CV: https://shees.dev

Email: [email protected]

GitHub: https://github.com/Realm07 (Under a rework)

Please check out my interactive 3D portfolio at https://shees.dev (built from scratch in Three.js w/ custom GLSL shaders, GSAP, and a full 3D scene I modeled in Blender).

Hey! I'm Shees. I'm a final year CS student and national-level hackathon winner who builds privacy-preserving systems, real-time graphics engines, and infrastructure applications.

Recent highlights: solo-authored an IEEE paper on secure federated learning, built an autonomous web-agent framework (AJATS) that automates job applications end-to-end, and engineered a full-stack ERP platform that boosted daily order volume by 40%. Won multiple hackathons with 800+ participants for a novel privacy-preserving federated ML platform, and another 600+ participant event for a real-time multiphysics engine & ML pipeline.

Experienced with 3D graphics, Performant Systems, Privacy-Preserving Technologies. Open to SWE, graphics, infrastructure, or security roles. Love owning systems end-to-end and making them from scratch, making them as optimized for performance and size as possible!