4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos
34,782 次观看
11 条评论
评论来自 X (Twitter) 上的原帖

@janusch_patas
Paper: not yet Project: "4DGT takes a series of monocular frames with poses as input. During training, we subsample the temporal frames at different granularity and use all images for supervision. In stage one, we train 4DGT to predict pixel-aligned Gaussians at coarse resolution. In stage two, we prune a majority of non-activated Gaussians based on the histograms of per-patch activation channels and densify the Gaussian prediction by increasing the input token samples in both space and time. At inference time, we run the 4DGT network trained after stage two, which supports dense video frames input at high resolution."
24 个赞

@janusch_patas
Paper:
6 个赞

@pablovelagomez1
Wow this looks really sick
4 个赞

@janusch_patas
Yeah, and the clip is super long.
1 个赞

@MickyAbir
people don’t realize how huge this is
1 个赞

@janusch_patas
long long videos, yeah!

@TessyXR
The fact that I can't get my head off this for the past few days... For me, it is that much needed tool that unlocks a lot.
1 个赞

@_troglobyte
Awesome. Looking forward to trying this out!
1 个赞

@janusch_patas
I'm crafting an email newsletter that turns my daily updates into a captivating weekly digest, complete with exclusive content. Although it's not live yet, you can sign up now! If you're curious, visit my website and join the subscriber list today!
1 个赞

@marknadal
the future is beaming into reality gaaah this is so exciting
1 个赞

@janusch_patas
Pretty good for monocular footage. The videos are also very long!
2 个赞
