[HN Gopher] Gaudi: A Neural Architect for Immersive 3D Scene Gen...
___________________________________________________________________
Gaudi: A Neural Architect for Immersive 3D Scene Generation
Author : andsoitis
Score : 72 points
Date : 2022-08-04 15:15 UTC (7 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| mistrial9 wrote:
| if this is an internal code-name OK, but this public post sounds
| more like a product name. How is it OK to hijack the widely-known
| artist, with no other meaning, for your commercial VR product ?
|
| "Antoni Gaudi i Cornet was a Catalan architect from Spain known
| as the greatest exponent of Catalan Modernism. Gaudi's works have
| a highly individualized, sui generis style. Most are located in
| Barcelona, including his main work, the church of the Sagrada
| Familia"
| LegitShady wrote:
| 100% correct. just borrowing credibility unearned.
| spywaregorilla wrote:
| Seems more like an homage than a hijacking?
| uoaei wrote:
| It's cute, but completely tone-deaf.
| spywaregorilla wrote:
| Why?
| zvr wrote:
| Not to mention the (trademarked) Gaudi processor for ML/AI:
| https://habana.ai/training/gaudi2/
|
| Wondering whether this Gaudi software can be ported to use
| Gaudi SDK :-)
| mistrial9 wrote:
| I am not OK with public social arts being rebranded for
| corporate PR
| cinntaile wrote:
| It's just a homage to an architect.
| yazzku wrote:
| No it's not, it's PR bullshit.
| zitterbewegung wrote:
| There is DALLE and Inception from other groups (openai and
| google ) . Also Big Bird and Bert. It's basically okay as long
| as anyone would find an issue or involve lawyers at least for
| Deep Learning researchers .
| klipt wrote:
| Dali -> DALL-E
|
| Gaudi -> GAUD-E?
| a9h74j wrote:
| Speaking of which, can you take DALL-E output and feed it
| in and get 3D art? Or maybe someday prompt-to-3D direct,
| although the right kind of training data might not be there
| yet.
| yazzku wrote:
| Why is this down-voted? Fuck the name appropriation for
| corporate PR.
| yazzku wrote:
| And I get down-voted too. Apple fanboys entered the chat?
| kemayo wrote:
| Complaining about voting gets you downvoted, pretty
| reliably. It's also against the community guidelines:
| https://news.ycombinator.com/newsguidelines.html
|
| EDIT: plus, I guess your second comment is insinuating
| about brigading, which is also against said guidelines. :D
| rgovostes wrote:
| Wait until you hear what they did to McIntosh apples and Isaac
| Newton.
| yarg wrote:
| Perhaps I'm wrong, but judging by the wibbly-wobbly walls, this
| is well behind the state of the art when it comes to the
| preservation of spatial invariants.
|
| By comparison a lot of the more recent demos are not only capable
| of polyframe structure preservation, but also do a very good job
| at preserving invariants even of subjects that are moving and
| deforming (such as a speaking human).
| heyitsguay wrote:
| Cool! Any demos you can link to?
| fezfight wrote:
| What's with the weird license? Where's the code? Looks cool,
| otherwise.
| Hnus wrote:
| > enables conditional generation of 3D scenes from different
| modalities like text or RGB images.
|
| Please help me understand few dumb questions I have.
|
| - What exactly is used as an input to generate such scenes is it
| just few pictures or even text description?
|
| - Is it able to generate data for something which was not in the
| input? Like you have some common object in the corner of your
| photo and its able to expand the picture as if you had it in the
| frame in the first place?
|
| - What is the end game of technologies like these? Could it be
| one day fed lets say every piece of data google has about the
| world like every 360 picture, every book, article, video, movie
| and so on allowing you to take picture of something and spawning
| infinitely walkable world looking and behaving as our reality?
| Similar to procedurally generated video game map.
| upupandup wrote:
| i think this takes a scene, pictures or videos and reconstructs
| a 3D scene where it recognizes entities.
|
| i dont think so? it just reconstructs the space it sees but it
| could absolutely expand to fill in the gap so to speak.
|
| robotic navigation and manipulation with environment would be
| my immediate guess. It would be able to build a complete 3D
| version of the world and recognize objects. Your idea could be
| a reality here as well.
|
| CVPR 2022 was a very interesting year for 3D scene
| reconstruction. One particular paper I recall was reaching into
| a database of CAD objects and simply replacing the scene with
| those objects that fit very close to what is shown in the
| scene. It could mean that a robot armed with this type of
| computer vision could manipulate with every single object it
| sees and know exactly how to interact with it without further
| examination.
| auggierose wrote:
| Is that a Wolfenstein texture I see there?
| coolspot wrote:
| Vizdoom dataset, yes
|
| http://vizdoom.cs.put.edu.pl/
___________________________________________________________________
(page generated 2022-08-04 23:01 UTC)