Is the lighting baked in like in the original paper or is it possible to relight the generated heads?
@spider254413 күн бұрын
Cant relight what you didn’t capture in the dataset.
@jonasmayer562417 күн бұрын
Incredible work! Also: Levenberg-Marquardt and gaussian splats... this has to be the most Mathias Niessner thing i've ever seen! :D
@RaspiAudio19 күн бұрын
Looks great but when do you plan to release your source code?
@mattanimation21 күн бұрын
awesome!
@0609Bhuwan22 күн бұрын
Wow this is great work...Congratulations to the team !!! Are we going to get to use this or is it only for use by synthesia ??
@김대현-t8c4k2 ай бұрын
Hello, I appreciate your outstanding research. I have a question. How do I create a scene with texture using a .obj file and an RGB texture image with resolution of 4096 x 4096?
@floribertjackalope26062 ай бұрын
is it intended that the course site was taken down?
@onurcanisler2 ай бұрын
Oh dear god. Surely the hardest lecture of all.
@mrburns3663 ай бұрын
So.. LA Noire 2? 😁
@AaliDGr83 ай бұрын
how to use it stpd act WTH did not you give us working link ??? plz
@weelianglien6873 ай бұрын
i wonder in the AlexNet (e.g. 1st conv layer) example, should the kernels be labelled as 11x11x3 due to the RGB, unless the usage of blue colour layers in all the stages signifies that this is only an illustration for the B layer?
@ONDANOTA3 ай бұрын
thanks! very informative
@alex233613 ай бұрын
fantastic
@OneOneTwo34 ай бұрын
My neurons do tend to dropout during tests.
@shishen52534 ай бұрын
Very impressive work!Will the code for this paper be open source?
@AR-vb4xy4 ай бұрын
Very interesting video but I suggest a improvement with respect to the display of the lecture: The block on the lower right where the recording of the professor is, should be very small or removed alltogether.
@adriangalvez798Ай бұрын
Yes please, sometimes it overlaps with the text/notation 🙏🙏🙏
@florisvanderhout267512 күн бұрын
Slides are in the description
@interfect4 ай бұрын
Thank you for the great lectures! Is it somehow possible to get the slides for parts 8-12?
@dddd-wf6fn4 ай бұрын
如果有很多万级带有语义的三维模型,是否可作为训练数据,用three.js加载后,自动输出训练数据?
@MisterWealth4 ай бұрын
When will the code be made available?
@shan_4205 ай бұрын
24:00 I think it's a bit confusing with f=Wx and in the image it's xW=f, specially when talking about the dimensionality of W.
@bakikucukcakiroglu5 ай бұрын
using the test data over and over again makes it the second phase validation data so doing that can be considered as skipping the test phase.
@rallyworld34175 ай бұрын
Impressive
@kasemir05 ай бұрын
body, how can i use this code on the Colab? please, help me. tks
@M_a_t_z_ee5 ай бұрын
Great introductory lecture. I'm excited about the following ones as well as the programming exercises. 😀
@yimloo605 ай бұрын
Thank you! Deep Learning! Thats my first time to recognize that i have a goddamn brain! :)
@eskimo26166 ай бұрын
19:11 what does "clamp it to zero" mean?
@ulascanzorer5 ай бұрын
I think it just means we set zero as our minimum so that the values can't go lower than that.
@M_a_t_z_ee5 ай бұрын
It means that you take two argments for the maximum function: 0 and the function based on previous inputs. This translates to the ReLU (rectified linear unit) activation function. If the second argument is bigger than 0, the max function evaluates to that argument. If the second arguments is negative, the max function evaluates to 0. It "clamping" all negative outputs from the previous layer to 0.
@DaveDFX6 ай бұрын
Amazing ! Game changer for avatars
@PakkaponPhongtawee6 ай бұрын
Could you please upload the supplementary material to the website? In the paper is mentioned that result in relighting can be found at relighting_results.html. and i want to look into how good it can be relight. Thank you.
@georgetang506 ай бұрын
Please release the code
@bilalse68626 ай бұрын
Very impressive paper, thank you guys !
@Copa207777 ай бұрын
This is great..❤
@wolpumba40997 ай бұрын
*ELI5 Abstract* *Imagine you have a magic drawing machine!* This machine can understand words and make pictures with just a description. But sometimes, the pictures only show the object from one side, like a flat drawing. *We made the machine even better!* Now it can learn from real photos of objects. We taught it how to make a 3D picture inside its head, so you can see the object from any side, as if it were real! *Our pictures are super cool!* We can tell the machine "a red bouncy ball" or "a fluffy brown dog," and it makes a picture that looks just like the real thing. You can even spin the picture around to see it from all angles. It's like magic! *Abstract* Recent advances in text-guided 2D image generation have spurred interest in 3D asset generation. However, existing text-to-3D methods often produce non-photorealistic objects lacking realistic backgrounds. In this work, we present ViewDiff, a method that leverages the power of pretrained text-to-image diffusion models to generate 3D-consistent images from real-world data. Our key innovation lies in integrating 3D volume rendering and cross-frame attention layers into a U-Net architecture. This enables our model to generate views of an object from any viewpoint in an autoregressive manner. Trained on real-world object datasets, ViewDiff produces instances with diverse, high-quality shapes, textures, and realistic backgrounds. Our results demonstrate superior visual quality and consistency compared to existing methods, as measured by FID and KID scores. disclaimer: i used gemini
@faruknane7 ай бұрын
Great work!
@dangthanhtuanit7 ай бұрын
I wonder if there is an actual implementation since code is not available?
@adrianstarfinger57217 ай бұрын
Impressive work!
@briancunning4237 ай бұрын
Amazing. Have you tried feeding the images into photogrammetry software or Gaussian Split software to test the consistency of the 3D?
@lukashollein39857 ай бұрын
Yes, this works! You can check the figures 17 to 19 in the paper: lukashoel.github.io/ViewDiff/static/viewdiff_paper.pdf
@manu.vision7 ай бұрын
😮
@couragefox7 ай бұрын
Really qant to try it. Please let us know if the code will be released...
@stevenlk7 ай бұрын
wow that’s impressive
@ritikkothari27877 ай бұрын
for calculating parameters of a particular layer, we do consider he size oof kernal (including depth) which i guess the professor missed! for example in vgg : for first layer - (3X3X3 + 1) * 64 for first layer and (3X3X64 + 1) *64 for the second layer.
@adrianstarfinger57217 ай бұрын
45:17 Here you talk about Neural Rendering, e.g. NERF which is using an MLP, and you call it an implicit function. However, in the first lecture we learned that MLP's are actually not implicit functions.