Code Monkey home page Code Monkey logo

seeingspace's Introduction

Sehender Raum / Seeing Space

Catching up with newer research in image based rendering: A TLDR on how traditional computer graphics will change with neural rendering. And how it fits with computer vision, machine learning and capture hardware.

With neural rendering computer graphics and vision might be heading for a moment where we can see and remove some limiting assumptions about what it is about. Some disjoint pieces may just fall into place: Computer graphics and vision now have a shared framework rather than being in nther own little boxes. We got things wrong and the possibilitis are exciting. I spent enternity on tools for generating photoreal 3d environments, now its easy as snap chat. We can have realtime google earth. I am allowed to be damned excited.

Moved to the WIKI of this repo.

Dont feel like reading but just want to try Nerfs yourself: Getting started-and Nerf frameworks

Overview and papers: Nice intro video https://www.youtube.com/watch?v=isKbsNKArJU https://youtu.be/sr1LG47J5uc?si=l4K59vOOlJyRv6KH nerf 101 video

1) Understanding Neural rendering (START HERE)

2) Nerf (radiance fields) basics, frameworks and real world uses

3) Nerf for 3d mapping: aka Google live view and Apple Fly around

4) Nerf Editing: Relighting, geometry extraction, scene segmentation

5) Dynamic and generative Nerfs: Text to nerf

6) Nerf rendering, compositing and web viewing

7) Related fields (Photogrametry, LIDAR, SLAM etc)

Hands on:

Join Nerf discord at https://discord.com/invite/atzsCcAXEh or the Nerfstudio discord at https://discord.gg/jKBErnzw and build the future with us

Why does it matter? It might be the biggest change change to graphics since the mid 80ies: We can now render lightfields, the holy grail of graphics. We know about light fields since 1908 but until 3 years ago they were just too expensive and impractical to create and render ("flying cars", possible but why do it?). You needed the camera on the picture below at least, now you render one from 30 frames of compressed video from youtube and a gaming machine or the cloud...

Getting hands on: Google colab setup for NVIDIA Instant Nerf, so you can try before buying a new gpu Step by step

seeingspace's People

Contributors

3a1b2c3 avatar katrinbschmid avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.