Introducing Marigold 🌼 - a universal monocular depth estimator, delivering incredibly sharp…
@AntonObukhov12702 位关注者
490,940 次观看
9 条评论
评论来自 X (Twitter) 上的原帖

@kwea123
70s of inference for an image is very slow..
9 个赞

@AntonObukhov1
We focus on the quality first - speed will come later through research and improvements in diffusion samplers. Arguably, Stable Diffusion is also slower than most of the GANs :)
42 个赞

@bilawalsidhu
Damn those are some crispy depth maps!
7 个赞

@chrisoffner3d
Wow, those depth maps look amazing. Great work! There goes my course project for Deep Learning. 😅
5 个赞

@BoyuanChen0
Is this metric or relative depth?
4 个赞

@AntonObukhov1
Relative
6 个赞

@janekm
I also consider this strong evidence that Stable Diffusion learned much stronger 3D scene understanding than commonly assumed.
4 个赞

@osanseviero
Very very cool!
3 个赞

@Tom14985282
Wow. More detailed than the ground truth, very cool to see.
3 个赞
