Gaussian Splatting explorations

Поделиться
HTML-код
  • Опубликовано: 28 ноя 2024

Комментарии • 59

  • @basiliotornado
    @basiliotornado Год назад +4

    I never would've thought style transfer possible like that! Nice video!

  • @camtrik3686
    @camtrik3686 Год назад +12

    Very nice video, thank you! Can you also share the notebook code you use in the video?

  • @datasciencecastnet
    @datasciencecastnet  Год назад +3

    Ha, guess who forgot to add the visual aids during the intro..... hand gestures will have to suffice ;) Paper and code show up from 6 minutes in.

  • @Wilqposnb
    @Wilqposnb Год назад +1

    i like this guy's personality

  • @ajamoffatt
    @ajamoffatt Год назад +1

    Jonathan thank you for the great walk through. The video structure is excellent. It is also really cool work you’re doing to stylize the base results!!

  • @dyllanusher1379
    @dyllanusher1379 Год назад

    I love the pace, the comedic timing, the content and animations!

  • @lion87563
    @lion87563 10 месяцев назад +1

    Guy with worst image quality ever explains technique that produces best image quality ever. Just some geek joke, thank you for such a nice presentation

  • @Mr_NeRF
    @Mr_NeRF Год назад +1

    Very nice video with very good explanation of the key concepts! Especially the sh are nicely explained.

  • @georhodiumgeo9827
    @georhodiumgeo9827 Год назад +6

    Bro your ChatGPT history looks a lot like mine, just tons of insane neerdy stuff.
    How fast is the retraining process? Like could you retrain a scene during gameplay with a good gpu? Especially if you had some trained gaussians already in place.
    I've been wanting to make a project like this for a while but I can't figure out a way to do it with mesh objects. What I want to do is have an AI NPC on level 1 start talking to you adout something, anything really and let the player lead the conversation. Lets say you mention clouds then it starts googling clouds and starts training based on that as a prompt. By the time you get to level 2 its ready and level 2 is based on some structure but everything has morphed into clouds.
    That would be nuts when you realize you are just manifesting your own game play with what you are talking with the NPC about.
    I was thinking about having some primative sphere for most objects then using picture to depth field from stable diffusion help reshape the mesh then wrap a new texture on it. I think it could work on a high end computer but this method seems like it would be almost a dreamy hasey way to do it. If you could buy some time in cut scenes and dialog interactions it might be possible.
    Anyway this whole process for rendering is just nuts. Trying to wrap my brain around it.

  • @monstercameron
    @monstercameron Год назад +10

    This is crazy interesting but no one is talking about it

    • @rmt3589
      @rmt3589 Год назад +4

      People just started talking about it. This is the second video on it I've watched today.

    • @hdslave
      @hdslave Год назад +2

      All github videos are like that. No one cares until it's integrated into some kind of consumer app. Ai stuff was the same way. Gan videos got no plays and no one was talking about ai until dalle and midjourny came out

    • @Instant_Nerf
      @Instant_Nerf Год назад +1

      We are busy working with it

    • @nicholassmit6875
      @nicholassmit6875 Год назад +2

      One month later, my feed is literally filled with it 😁

    • @呂皓恩
      @呂皓恩 10 месяцев назад

      It is starting to blow up

  • @grantbaxter554
    @grantbaxter554 11 месяцев назад

    Very cool, very well explained, thank you

  • @MikeTheAnomaly
    @MikeTheAnomaly Год назад

    Wonderful explanation! Thank you!

  • @DiegoBarreiroClemente
    @DiegoBarreiroClemente Год назад

    Great video and explanation Jonathan! I really enjoyed your approach with CLIP to be able to modify gaussians given a text prompt.
    Do you have a link to the jupyter notebook you used in the video?

  • @Ali-wf9ef
    @Ali-wf9ef 8 месяцев назад

    It would've been cool if you could visualize which point in the scene you are showing the spherical harmonics for

  • @naninano8813
    @naninano8813 Год назад

    well spherical harmonics (thanks for the explanation btw) are cool and all but they are not adequate way of modeling light caustics. like if you have something refractive in your scene, like a half full glass of water, I wonder if splats can represent how objects behind it would warp. and re-lighting a splat scene (adding a light source, post capture) is tricky IMO

  • @itsm0saan
    @itsm0saan Год назад +1

    thanks for the video ❤! As a suggestion, Would like to see something about peft (LoRa, Quantization …..)

  • @adityakompella9203
    @adityakompella9203 Год назад +2

    Would it be possible to post the notebook that you walk through in the video?

  • @BradleySmith1985
    @BradleySmith1985 Год назад

    this will be the new live AR option.

  • @HaiweiShi
    @HaiweiShi 5 месяцев назад

    Hi, really good video. Could you share the jupyter notebook you showed in this video? It would be so grateful!

  • @MattCruikshank
    @MattCruikshank Год назад +2

    Can you say the final size of the scene, especially compared to the size of the input images and the number of iterations? Would it be viable to embed the scene representation into a video game, for instance, or are they enormous? (Or would we need to use something like Wavelets to represent the scene, and transform back into these harmonic values before rendering?)

  • @WhiteDragon103
    @WhiteDragon103 Год назад +6

    Do the gaussians model view direction dependent effects? Or are they best suited to only represent lambertian materials?
    E.g. can specular highlights, refractions, non-planar reflections, fresnel effects, etc. be modelled using these?
    If so, how? As far as my understanding goes, these gaussians are basically single-colored blobs, similar to billboards (as used by particle effects for games).

    • @datasciencecastnet
      @datasciencecastnet  Год назад +3

      They model directional effects using something called spherical harmonics, where the color of a gaussian depends on the viewing angle. It isn't perfect, but it let's you get the appearance of reflections and shine.

    • @WhiteDragon103
      @WhiteDragon103 Год назад +1

      @@datasciencecastnet I see.
      SH is efficient for representing lighting as used by diffuse (e.g. lambertian) surfaces, as you only need 4 parameters per color channel.
      However, I've seen their technique produce sharp reflections (the red sports car has a sharp reflection on the hood). For this to be possible using vanilla SH, you'd need an impractical number of parameters per gaussian.
      Are they perhaps passing the output color returned by the SH calculation through a clamp or sigmoid, so that sharp edges can form when using very high magnitude SH coefficients?

    • @datasciencecastnet
      @datasciencecastnet  Год назад +2

      @@WhiteDragon103 they use 3rd degree SH (so 16 coefficients in total), as far as I know no extra clamping or activation functions.

  • @er-wl9sy
    @er-wl9sy Год назад

    Thanks. Could you go over the CUDA code as well

  • @Nik-dz1yc
    @Nik-dz1yc Год назад +1

    I'm curious though; Weren't there differential renderers with spherical harmonics already a thing since like 2008 ?

  • @quyet-65cs3buivan8
    @quyet-65cs3buivan8 5 месяцев назад

    very interesting, thank you! Can you also share the notebook code of your on this video?

  • @ParinithaRamesh-qf2ig
    @ParinithaRamesh-qf2ig 5 месяцев назад

    Can you please share the git repo for all your code, it would be great to follow along and see the results on my end.

  • @pouljensen2789
    @pouljensen2789 11 месяцев назад

    Can splats emit light (instead of just reflecting)? If not, how difficult would that be to implement? I'd like to try modelling aurora, which would correspond to fully transparent splats emitting light.

  • @dl569
    @dl569 10 месяцев назад

    thanks, very clear!

  • @gridvid
    @gridvid Год назад +3

    Can you also model, texture, light and animate than render with this tech?

    • @Dan-gs3kg
      @Dan-gs3kg Год назад +1

      It's a voxel representation, the notion of texture gets difficult to talk about since there are no texels.
      For lighting, the spherical harmonics could be of interest as that implements anisotropy, allowing for reflections. The issue is how to do that efficiently, at base you can make the underlying exist in linear color space by which you can apply highlights and shading on top of that with traditional methods.
      For animation, you need to define animations in terms of point clouds, instead of textured models.

    • @gridvid
      @gridvid Год назад +1

      @@Dan-gs3kg but you could create fictional, photorealistic worlds in blender, render those cgi scenes with circles from different perspectives and use those images to create realtime representations with this tech... or not?
      Lightning is certainly interesting 🤔 Each Gaussian Slat would need to have information about its roughness I think

    • @DamonHenson
      @DamonHenson Год назад

      They're not voxels - they're an arbitrary amount of objects in a given space at continuous positions. Voxels are defined along more of a discrete grid.@@Dan-gs3kg

  • @specyfickRC
    @specyfickRC 9 месяцев назад

    Can you share this code you have made for this video ?

  • @aintgonhappen
    @aintgonhappen Год назад

    the description is missing the link to the paper website 😥

  • @optus231
    @optus231 4 месяца назад

    Where is this? "GS website (with links to paper):"

  • @李应健
    @李应健 Год назад +1

    nice

  • @mort_brain
    @mort_brain Год назад

    So, but it doesn't use any poligonal meshes so you can't use it with other techniques, or can you?

    • @datasciencecastnet
      @datasciencecastnet  Год назад

      No meshes or triangles here! There is some work being done on how to extract meshes from these gaussian representations but it's tricky to do that well.

  • @philtoa334
    @philtoa334 Год назад

    Very Good.

  • @pajeetsingh
    @pajeetsingh Год назад

    High Fidelity? Fidelity?

  • @yuvish00
    @yuvish00 8 месяцев назад

    Can you share the code please?

  • @Mitobu1
    @Mitobu1 Год назад

    I wonder if this would work with a laplacian distribution rather than a gaussian 🤔

    • @laurenpinschannels
      @laurenpinschannels Год назад

      what's your reasoning for why to do that?

    • @Mitobu1
      @Mitobu1 Год назад +1

      @@laurenpinschannels well laplacian distributions are like really narrow gaussians with long skinny tails, and is a powerful tool used in source localization. It is also prevalent in how neurons organize themselves to support sparse coding, which can be applied in pruning the neural network.

  • @ScientiaFilms
    @ScientiaFilms Год назад

    Is there a way to continue training from a previously unfinished training?

  • @flowerflower1154
    @flowerflower1154 Год назад

    The quality of your facecam looks like being in 2002

  • @Nekzuris
    @Nekzuris Год назад +1

    The video looks like it's from before 2010

  • @Autovetus
    @Autovetus Год назад +1

    So prince Harry is now an IT nerd ?? 🤔