ff_magic_leap-eric_browy-929×697

Leave a Reply Cancel reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Retweet on Twitter Luigi Freda Retweeted

17 Jul

No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations

Walter Simoncini, Spyros Gidaris, @abursuc , Yuki M. Asano
tl;dr: gradients from augmentation-supervised obj at test time, concatenated with features improve your descriptor
https://arxiv.org/abs/2407.10964

Reply on Twitter 1813542921859396090 Retweet on Twitter 1813542921859396090 29 Like on Twitter 1813542921859396090 99 Twitter 1813542921859396090

Retweet on Twitter Luigi Freda Retweeted

Dmytro Mishkin 🇺🇦 @ducha_aiki ·

11 Jul

MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo
Tianqi Liu, Guangcong Wang, Shoukang Hu, Liao Shen, Xinyi Ye, Yuhang Zang, Zhiguo Cao, Wei Li, Ziwei Liu

tl;dr: similar to MVSplat,less transformer, more CNN, more GS
https://arxiv.org/abs/2405.12218

Reply on Twitter 1811353899900490112 Retweet on Twitter 1811353899900490112 10 Like on Twitter 1811353899900490112 53 Twitter 1811353899900490112