LogoThread Easy
  • 探索
  • 撰写 Thread
LogoThread Easy

您的一体化 Twitter 线程助手

© 2025 Thread Easy All Rights Reserved.

探索

最新在前,按卡片方式浏览线程

开启时会模糊预览图,关闭后正常显示

UTrice: Unifying Primitives in Differentiable Ray Tracing and Rasterization via Triangles for Particle-Based 3D Scenes

Contributions:
• We propose an optimization pipeline for ray-traced, particle-based radiance fields using triangles as primitives.

• We introduce a differentiable formulation that enables triangles to serve as optimizable primitives within the ray tracing pipeline.

• We demonstrate that using triangles as primitives yields better generality and higher rendering quality compared to Gaussian-based representations.

UTrice: Unifying Primitives in Differentiable Ray Tracing and Rasterization via Triangles for Particle-Based 3D Scenes Contributions: • We propose an optimization pipeline for ray-traced, particle-based radiance fields using triangles as primitives. • We introduce a differentiable formulation that enables triangles to serve as optimizable primitives within the ray tracing pipeline. • We demonstrate that using triangles as primitives yields better generality and higher rendering quality compared to Gaussian-based representations.

Paper: https://t.co/7fdjcRzLwa Code: https://t.co/cUVLlmqjp3

avatar for MrNeRF
MrNeRF
Fri Dec 05 08:07:10
I'm telling you - Serverless is not suited for a proper backend. It has its usage - Parqet Wrapped uses it a LOT.

5 years ago, the Parqet backend was hosted on Serverless - after switching to a proper backend performance was up 3000%.

Don't reinvent the wheel.

I'm telling you - Serverless is not suited for a proper backend. It has its usage - Parqet Wrapped uses it a LOT. 5 years ago, the Parqet backend was hosted on Serverless - after switching to a proper backend performance was up 3000%. Don't reinvent the wheel.

Founder 📈 @parqetapp Host of 🎙 @minimalempires Prev. @stripe

avatar for Sumit Kumar
Sumit Kumar
Fri Dec 05 08:02:38
Makes perfect sense, but still a nice finding. Maybe with the kind of compute we now have and a renewed focus on small models a la @Dorialexander, it'll even be practically usable for baking powerful cognitive cores that can be continuously updated.

Makes perfect sense, but still a nice finding. Maybe with the kind of compute we now have and a renewed focus on small models a la @Dorialexander, it'll even be practically usable for baking powerful cognitive cores that can be continuously updated.

We're in a race. It's not USA vs China but humans and AGIs vs ape power centralization. @deepseek_ai stan #1, 2023–Deep Time «C’est la guerre.» ®1

avatar for Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)
Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)
Fri Dec 05 08:00:49
| ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄|
|Don'tPushToProductionOn______|
|________________|
                       \ (•◡•) /
                         \      /
                          ——
                          |      |
                          |_    |_

| ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄ ̄| |Don'tPushToProductionOn______| |________________| \ (•◡•) / \ / —— | | |_ |_

We're sharing/showcasing best of @github projects/repos. Follow to stay in loop. Promoting Open-Source Contributions. UNOFFICIAL, but followed by github

avatar for GitHub Projects Community
GitHub Projects Community
Fri Dec 05 08:00:07
Slow slow growth of my AI Coding newsletter.

Now 600 subscribers, ~100 per month.

This is how many products actually grow.
In a slow, boring, grinding way.

And that's why a lot of them are abandoned, because they just don't survive long enough.
Creators lose the motivation, that's natural.

But actually, quite often there's a breakthrough on the horizon - one viral post, one partnership with some influencer, one topic that "hits hard" - and then you're "suddenly" famous.

So yeah, will keep grinding until I find those breakthroughs.

P.S. Subscribe if you're interested in my AI Coding experiments, I email them every Wednesday, for free:

Slow slow growth of my AI Coding newsletter. Now 600 subscribers, ~100 per month. This is how many products actually grow. In a slow, boring, grinding way. And that's why a lot of them are abandoned, because they just don't survive long enough. Creators lose the motivation, that's natural. But actually, quite often there's a breakthrough on the horizon - one viral post, one partnership with some influencer, one topic that "hits hard" - and then you're "suddenly" famous. So yeah, will keep grinding until I find those breakthroughs. P.S. Subscribe if you're interested in my AI Coding experiments, I email them every Wednesday, for free:

~20 yrs in web-dev, now mostly Laravel. My Laravel courses: https://t.co/HRUAJdMRZL My Youtube channel: https://t.co/qPQAkaov2F

avatar for Povilas Korop | Laravel Courses Creator & Youtuber
Povilas Korop | Laravel Courses Creator & Youtuber
Fri Dec 05 07:58:01
Paper: https://t.co/pglYMh9oyw
Project: https://t.co/8KZtkRzsY7
YouTube: https://t.co/FTZehV5PVn

Paper: https://t.co/pglYMh9oyw Project: https://t.co/8KZtkRzsY7 YouTube: https://t.co/FTZehV5PVn

Founder and CEO of https://t.co/5MjtfpwEU3 | Your guide to radiance fields | Host of the podcast @ViewDependent | FTP: 279 | discord: https://t.co/lrl64WGvlD

avatar for MrNeRF
MrNeRF
Fri Dec 05 07:56:43
  • Previous
  • 1
  • More pages
  • 1529
  • 1530
  • 1531
  • More pages
  • 5634
  • Next