Yingda Yin
Yingda Yin
Just like the name of a figure except the tag
As mentioned in #46, directly fitting a 2D bbox by the projected vertices of 3D bbox can be very inaccurate. For example, the actual 2d bbox in green and the...
Thanks for the solid and impressive work! The PatchNCE loss works for content preservation. In the paper, the multi-scale feature extraction is done by the readily available generator encoder. What...
Hi. Thanks for your great work of ANL. I'm trying to reproduce the work on a scanned 3D environment (like Gibson). Unfortunately, I met some problems. I'd appreciate it if...
As shown, $\lambda_1$ does not appear in the sidebar 
Like this nice work of rl codebase. It's nice and pretty! I wonder if there is any evaluation examples? I mean we have `build and train`, but do we have...
Hi, thanks for the great work! Following the repo of DeepSDF https://github.com/facebookresearch/DeepSDF, I preprocess the ShapeNetV2 data and train the network on Car category. Suprisingly, compared with the pretrained models...
For everything mode, the results of the live demo are different from those of the code. This issue has been raised in #54, https://github.com/facebookresearch/segment-anything/issues/147#issuecomment-1580320230, #330, and #346, and unfortunately, we...
When the title is an inline equation, the outliner does not appear well. This occurs with the newest enhancer release. Please see https://yingda.notion.site/test-902aa1a64b1a4bbdae9ac6981ea9168b for the test page. 
Hi, thanks for your really great work! Just a silly question, for this "full-body pose tracking from sparse motion sensing" task, how are the leg poses estimated, intuitively? I think...